b6af371105
docs: catalog llm-finetuning + dgx-spark-ops skills/commands, fix dgx-spark-ops description
...
- agent-skills.md: add LLM Fine-Tuning (10 skills) and DGX Spark Ops (3 skills) sections
- usage.md: add /llm-finetuning:finetune, /llm-finetuning:promote-checkpoint, /dgx-spark-ops:spark-preflight to command reference
- plugins.md: correct dgx-spark-ops description (NVIDIA GB10 workstation ops, not Apache Spark cluster)
2026-07-14 13:36:44 -04:00
baa5bd7997
feat: add llm-finetuning and dgx-spark-ops plugins (eval-gated fine-tuning lifecycle) ( #624 )
...
* feat(dgx-spark-ops): scaffold plugin and register in marketplace
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(dgx-spark-ops): add spark-environment-setup skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(dgx-spark-ops): tighten spark-environment-setup per review
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(dgx-spark-ops): add spark-training-gotchas skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(dgx-spark-ops): align preflight.sh output contract with docs
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(dgx-spark-ops): add spark-memory-thermal-ops skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(dgx-spark-ops): trim spark-memory-thermal-ops and source 68GB anchor
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(dgx-spark-ops): add dgx-spark-ops-engineer agent
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(dgx-spark-ops): defer agent facts to skills
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(dgx-spark-ops): add /spark-preflight command
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): scaffold plugin and register in marketplace
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add finetuning-method-selection skill with dated model catalog
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add lora-qlora-recipes skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add preference-optimization skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add grpo-rlvr-training skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): add isolation warning to execution reward
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add vision-sft skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add dataset-curation skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): correct loss-masking example in dataset-curation
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add eval-harness-first skill (Phase 0 gate)
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): bring eval-harness-first into line band
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): reclaim byte headroom in eval-harness-first
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add trace-to-training-data skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add checkpoint-promotion skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add quantized-export skill
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add llm-finetuning-architect agent
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add llm-finetuning-training-engineer agent
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add llm-finetuning-eval-engineer agent
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add /finetune phase-gated lifecycle command
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): thread checkpoint path into /finetune Phase 6
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* feat(llm-finetuning): add /promote-checkpoint command
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): thread checkpoint path via phase5.output in /promote-checkpoint
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix(llm-finetuning): robust checkpoint discovery and goldens fingerprint in re-gate
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* docs: register llm-finetuning and dgx-spark-ops (94 plugins, 203 agents, 175 skills, 109 commands)
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* docs(agents): add fine-tuning and spark-ops agent entries (203 agents)
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* chore: generate per-harness artifacts for llm-finetuning and dgx-spark-ops
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix: final-review cleanups for fine-tuning plugins
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix: address PR #624 review feedback (G1 NGC detection, Phase 3 fallback dispatch, registry metadata)
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix: enforce sandbox boundary in execution grader and reward examples
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix: address CodeRabbit review findings on PR #624
Verified and fixed 37 of 43 outstanding CodeRabbit findings across the
llm-finetuning and dgx-spark-ops plugins (skipping 6 confirmed false
positives/already-fixed, with reasons in the disposition report).
Highlights: cross-file contracts (goldens fingerprint persistence,
paired-arena stage numbering, canonical golden-ID field, RERUN
resolution before promotion) now match between finetune.md,
promote-checkpoint.md, and checkpoint-promotion's templates. TRL API
usages (SFTConfig.max_length, trl.experimental ORPO/CPO imports)
verified against live TRL docs rather than blindly renamed. Several
runnable examples hardened against real failure modes: malformed
judge output, empty arena results, non-distinct DPO pairs, unbounded
rejection-sampling fan-out, non-deterministic smoke-test comparisons,
silent FP8-to-bf16 fallback, and orphaned background thermal-sampler
processes. Container detection (G9) and LoRA adapter-size math fixed
in both dgx-spark-ops and llm-finetuning where the same bugs were
independently present in each plugin.
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix: apply dogfood friction-log remediations (F1-F32) from DGX Spark run
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
* fix: address CodeRabbit round-2 findings (digest pins, suite-size math, monkeypatch scoping)
Claude-Session: https://claude.ai/code/session_01RsN3Vz5fZRTdVMkNtmxhSf
2026-07-14 13:18:02 -04:00
d7cf7dca8c
docs: sync counts to 92 plugins after hermes-tweet + ciagent merges ( #582 , #614 ) ( #616 )
...
Reconcile plugin-count references across AGENTS.md (==CLAUDE.md), docs/architecture.md,
docs/plugins.md, and docs/usage.md to 92 plugins (88 local + 4 external). The #582 and
#614 merges each updated only a subset of count strings; this brings the rest in line.
Agents (199), skills (162), commands (106) unchanged.
Verified: make validate STRICT=1, garden (0 err), test (449 passed), smoke-test (7 passed).
2026-07-08 10:32:14 -04:00
9c56144ace
docs: sync counts after skill-forge-essentials merge (90 plugins, 161 skills) ( #615 )
...
Recounted from the filesystem: 90 plugins (87 local + 3 external),
161 skills across 45 plugins. Also catches docs/usage.md and
docs/plugins.md install-note lines missed by earlier syncs.
2026-07-07 19:48:06 -04:00
9ab47ec442
docs: reconcile counts and catalog after batch plugin merge
...
After merging #575 (storymap-skill), #568 (runapi-mcp), #578
(before-you-build), #576 (file-conversion), #594 and #597 , reconcile the
marketplace/doc counts to the true totals: 88 plugins (85 local + 3
external), 194 agents, 158 skills, 106 commands. Add catalog rows for
runapi-mcp (AI & ML) and storymap-skill (Workflows, external); fix the
defi-protocol-templates skills-table line (lending -> flash loans).
2026-06-25 11:55:58 +09:00
f661b956ba
feat: add before-you-build plugin
2026-06-12 19:28:44 +08:00
767d969a73
docs: sync plugin/agent/skill counts to 84/192/156 after social-publishing merge
...
PR #558 updated the headline totals but left trailing references at
83/191/155 across README, AGENTS.md, GEMINI.md, ARCHITECTURE.md, and
docs/*. Sync them all to the true counts (82 local + 2 external = 84
plugins, 192 agents, 156 skills).
Also runs make generate-all to bring the committed harness registries in
sync — adds the social-publishing entries to .agents/ and .cursor-plugin/
(which the original PR could not regenerate) and fixes the stale count in
the generated cursor manifests.
Left round-trip-results.md (point-in-time CLI verification results) and
plugin-eval.md (grade threshold) unchanged.
2026-06-02 19:15:30 -04:00
9834a5f38d
Add Pensyve external integration ( #552 )
...
* feat: add Pensyve external integration
* docs: fix skill plugin count
2026-05-24 17:35:47 -04:00
9f9ba32370
docs: synchronize plugin/agent/skill counts ( closes #517 ) ( #522 )
...
* docs: synchronize plugin/agent/skill counts (closes #517 )
Live counts are 80 local plugins (81 incl. external git-subdir),
185 agents, 153 skills, 100 commands. Six docs were stale:
- marketplace.json metadata.description: 79/184/150 -> 80/185/153
- docs/plugins.md: 78 plugins (77 local) -> 81 plugins (80 local)
- docs/agents.md: 184 agents -> 185
- docs/agent-skills.md: 150 skills / 37 plugins -> 153 skills / 40 plugins
- docs/architecture.md: 79 plugins, 99 agents, 150 skills -> 81/185/153
- docs/usage.md: 150 skills, 79 plugins -> 153 skills, 80 plugins
Companion to 159ce68#522 :
- docs/agents.md model distribution table summed to 99 (42+39+18) but
the header now says 185 agents. Recounted from frontmatter:
opus 54, sonnet 62, haiku 20, inherit 49 = 185. Added the missing
Inherit row.
- docs/architecture.md model distribution table had the same stale
42/39/18 sum; updated to 54/62/20/49 and renamed "Two-Tier" to
"Four-Tier" since Inherit is now load-bearing.
- docs/architecture.md "average plugin size: 3.4 components" → 5.5,
matching (185 + 153 + 100) / 80.
- docs/plugins.md headline reframed from "81 ... 80 local + 1 external"
to "80 ... plus 1 externally-hosted" to match the GEMINI.md
path-based rule (catalog headline counts local plugins).
2026-05-09 11:16:26 -04:00
6625d1ead4
docs: refresh counts for protect-mcp + qa-orchestra; add CI validation
...
- Counts now reflect 79 plugins (77 local + 2 external via git-subdir),
184 agents, 150 skills, 98 commands across 25 categories
- README/docs: add Governance category (protect-mcp), bump Testing to 2
(adds qa-orchestra), expand Security table to include reverse-engineering
and block-no-verify, add Protect MCP skills section, surface pensyve in
AI & ML
- marketplace.json: bump metadata to 1.6.0, bump pensyve to 1.2.0
- Add .github/workflows/validate.yml to gate PRs on:
- marketplace.json + every plugin.json + hooks.json parse as JSON
- every ./plugins/<name> source resolves on disk with a plugin.json
- plugin-eval pytest suite (would have caught the #482 sdk.stream bug class)
2026-04-16 13:10:31 -04:00
03d0b4b9eb
docs: refresh counts and add missing sections after recent plugin merges
...
- README and docs now reflect 77 plugins / 182 agents / 149 skills / 96 commands
- agent-skills.md: add 9 missing plugin sections (agent-teams, reverse-engineering,
startup-business-analyst, shell-scripting, database-design, documentation-standards,
dotnet-contribution, plugin-eval, block-no-verify) covering 23 previously
undocumented skills; fix python-development from 5 to 16 skills
- plugins.md: correct 8 stale category counts and add missing Creative section
- agents.md: fix header from 100 to 182 agents
- architecture.md, usage.md: update plugin and skill counts
- README: surface HADS and block-no-verify in their categories, add 5 categories
that had been omitted (Creative, Accessibility, API, Utilities, Modernization)
Also a one-line follow-up to #462 : team-composition-patterns/SKILL.md line 136
in the Troubleshooting section still referenced the old Task tool — updated to
the current Agent tool name.
2026-04-08 17:37:48 -04:00
682abfcdeb
fix: remove stale code-review-ai plugin ( #134 , #135 )
...
Plugin had inconsistent content (OpenAI references, CI/CD workflow baked
into review command). Replaced by official pr-review-toolkit and
comprehensive-review plugins. Also answered discussions #138 , #421 , #422 .
2026-02-19 14:21:59 -05:00
f662524f9a
feat: add Conductor plugin for Context-Driven Development
...
Add comprehensive Conductor plugin implementing Context-Driven Development
methodology with tracks, specs, and phased implementation plans.
Components:
- 5 commands: setup, new-track, implement, status, revert
- 1 agent: conductor-validator
- 3 skills: context-driven-development, track-management, workflow-patterns
- 18 templates for project artifacts
Documentation updates:
- README.md: Updated counts (68 plugins, 100 agents, 110 skills, 76 tools)
- docs/plugins.md: Added Conductor to Workflows section
- docs/agents.md: Added conductor-validator agent
- docs/agent-skills.md: Added Conductor skills section
Also includes Prettier formatting across all project files.
2026-01-15 17:38:21 -05:00
01d93fc227
feat: add 5 new specialized agents with 20 skills
...
Add domain expert agents with comprehensive skill sets:
- service-mesh-expert (cloud-infrastructure): Istio/Linkerd patterns, mTLS, observability
- event-sourcing-architect (backend-development): CQRS, event stores, projections, sagas
- vector-database-engineer (llm-application-dev): embeddings, similarity search, hybrid search
- monorepo-architect (developer-essentials): Nx, Turborepo, Bazel, pnpm workspaces
- threat-modeling-expert (security-scanning): STRIDE, attack trees, security requirements
Update all documentation to reflect correct counts:
- 67 plugins, 99 agents, 107 skills, 71 commands
2025-12-16 16:00:58 -05:00
16cddabb75
add c4 documentation workflow and agents ( #129 )
...
* add c4 documentation workflow and agents
* update the c4-code agent to use proper mermaid diagram types
2025-12-10 14:53:11 -05:00
65e5cb093a
feat: add Agent Skills and restructure documentation
...
- Add 47 Agent Skills across 14 plugins following Anthropic's specification
- Python (5): async patterns, testing, packaging, performance, UV package manager
- JavaScript/TypeScript (4): advanced types, Node.js patterns, testing, modern JS
- Kubernetes (4): manifests, Helm charts, GitOps, security policies
- Cloud Infrastructure (4): Terraform, multi-cloud, hybrid networking, cost optimization
- CI/CD (4): pipeline design, GitHub Actions, GitLab CI, secrets management
- Backend (3): API design, architecture patterns, microservices
- LLM Applications (4): LangChain, prompt engineering, RAG, evaluation
- Blockchain/Web3 (4): DeFi protocols, NFT standards, Solidity security, Web3 testing
- Framework Migration (4): React, Angular, database, dependency upgrades
- Observability (4): Prometheus, Grafana, distributed tracing, SLO
- Payment Processing (4): Stripe, PayPal, PCI compliance, billing
- API Scaffolding (1): FastAPI templates
- ML Operations (1): ML pipeline workflow
- Security (1): SAST configuration
- Restructure documentation into /docs directory
- agent-skills.md: Complete guide to all 47 skills
- agents.md: All 85 agents with model configuration
- plugins.md: Complete catalog of 63 plugins
- usage.md: Commands, workflows, and best practices
- architecture.md: Design principles and patterns
- Update README.md
- Add Agent Skills banner announcement
- Reduce length by ~75% with links to detailed docs
- Add What's New section showcasing Agent Skills
- Add Popular Use Cases with real examples
- Improve navigation with Core Guides and Quick Links
- Update marketplace.json with skills arrays for 14 plugins
All 47 skills follow Agent Skills Specification:
- Required YAML frontmatter (name, description)
- Use when activation clauses
- Progressive disclosure architecture
- Under 1024 character descriptions
2025-10-16 20:33:27 -04:00
Seth Hobson