claude-skills

scriptoriumadmin/claude-skills

Fork 0

mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-10-07 02:58:13 +00:00

Commit graph

Author	SHA1	Message	Date
Claude	a088c8ba77	fix: phantom-path sweep — 888 unresolvable references to zero A directory reorg added a skills/ path segment; hundreds of references never followed. This sweep repoints every path-like reference in SKILL.md, agents, commands, orchestration, and templates to verified on-disk targets: - 30 root commands + 19 root agents: missing skills/ segment inserted - 7 c-level persona agents: 17 hallucinated reference filenames substituted with the real files (e.g. okr_execution.md -> process_frameworks.md) - 5 research skills: phantom scripts/office/validate.py step replaced with a runnable stdlib zip-integrity check - email agents: skills frontmatter corrected to productivity/email - orchestration/ORCHESTRATION.md + templates: stale paths fixed; agent-template now requires trigger phrasing in descriptions (root cause) - 76 more files across engineering, c-level-advisor, compliance-os, research-ops, ra-qm, marketing, productivity; dual-publish pairs mirrored - dead refs dropped/replaced where no target ever existed (REGISTRY.md, trend_analyzer.py, cursor-microinteractions.md) New: scripts/check_paths.py linter (CI gate G1) + narrow allowlist for teaching examples. Verified: 540 files scanned, 0 unresolvable. https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF	2026-06-10 14:33:00 +00:00
Claude	20589251ee	feat(research-ops): per-skill onboarding + customization + isolated autoresearch bridge Connects each research-ops sub-skill to engineering/autoresearch-agent and adds per-skill onboarding with a customization approach that the tools actually consume. Each sub-skill (clinical-research, research-finance, market-research, product-research) now ships three integration scripts: - onboard.py — its own onboarding questionnaire; interactive or --defaults / --set key=value / --reset / --scope; writes ~/.config/research-ops/<skill>.json (global) or ./.research-ops/<skill>.json (project). - config_loader.py — loads that config (project > global > defaults; RESEARCH_OPS_NO_CONFIG=1 bypass). Every scoring tool now reads it so saved answers change behavior: default profile, thresholds (alpha/power/dropout, F&A rate, runway, confidence, MoE, insight source-threshold), and named owners printed on clinical/finance outputs. CLI flags always override. - ar_evaluator.py — an isolated, OPT-IN ground-truth evaluator bridging to autoresearch. The loop edits the skill's input file and the evaluator (never edited) scores it: clinical feasibility_composite (higher), finance runway_months (higher), market tam_divergence (lower), product validated_insights (higher). No cross-skill coupling; invoked only on explicit user request. SKILL.md (each), the orchestrator, the agent, per-skill commands, and the domain CLAUDE.md document the onboarding + opt-in autoresearch handoff. plugin.json / marketplace describe 24 tools (12 analysis + 12 integration). Builds the cross-platform plugins: codex symlinks + gemini SKILL.md mirrors + vibe symlinks materialized for all 5 research-ops skills; indices regenerated. Root CLAUDE.md scope/highlights updated. https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D	2026-05-27 00:54:22 +00:00
Claude	caafb47daf	feat(research-ops): add enterprise Research Operations domain New top-level research-ops/ domain — the managed, cross-functional counterpart to the academic research/ domain. Single domain plugin (commercial/ pattern): orchestrator (context: fork) + 4 sub-skills: clinical-research (study design), research-finance (R&D program finance), market-research (sizing/survey/segmentation methodology), product-research (user-research method + insight repository). 12 stdlib-only deterministic Python tools (all pass --help/--sample/--output json), 12 reference docs (5-7 sources each), 4 asset templates, a cs-research-ops-orchestrator agent, and 6 commands (router + grill + 4 per-skill). Hard rules enforced via persona + anti-patterns: clinical outputs are estimates with a named clinical owner, finance routes capitalize-vs-expense to a named finance owner, market sizes show method (both ways) + assumptions, product insights require cross-participant recurrence. Explicit distinct_from framing keeps clear of ra-qm-team, finance, research/grants, product-team, and marketing-skill. Registered in marketplace.json (61 -> 62 plugins) and the codex/gemini/ hermes/vibe sync scripts + generate-docs; root CLAUDE.md bumped to v2.9.0. https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D	2026-05-27 00:31:27 +00:00

Author

SHA1

Message

Date

Claude

a088c8ba77

fix: phantom-path sweep — 888 unresolvable references to zero

A directory reorg added a skills/ path segment; hundreds of references never
followed. This sweep repoints every path-like reference in SKILL.md, agents,
commands, orchestration, and templates to verified on-disk targets:

- 30 root commands + 19 root agents: missing skills/ segment inserted
- 7 c-level persona agents: 17 hallucinated reference filenames substituted
  with the real files (e.g. okr_execution.md -> process_frameworks.md)
- 5 research skills: phantom scripts/office/validate.py step replaced with a
  runnable stdlib zip-integrity check
- email agents: skills frontmatter corrected to productivity/email
- orchestration/ORCHESTRATION.md + templates: stale paths fixed;
  agent-template now requires trigger phrasing in descriptions (root cause)
- 76 more files across engineering, c-level-advisor, compliance-os,
  research-ops, ra-qm, marketing, productivity; dual-publish pairs mirrored
- dead refs dropped/replaced where no target ever existed (REGISTRY.md,
  trend_analyzer.py, cursor-microinteractions.md)

New: scripts/check_paths.py linter (CI gate G1) + narrow allowlist for
teaching examples. Verified: 540 files scanned, 0 unresolvable.

https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF

2026-06-10 14:33:00 +00:00

Claude

20589251ee

feat(research-ops): per-skill onboarding + customization + isolated autoresearch bridge

Connects each research-ops sub-skill to engineering/autoresearch-agent and adds
per-skill onboarding with a customization approach that the tools actually consume.

Each sub-skill (clinical-research, research-finance, market-research,
product-research) now ships three integration scripts:
- onboard.py        — its own onboarding questionnaire; interactive or
                      --defaults / --set key=value / --reset / --scope; writes
                      ~/.config/research-ops/<skill>.json (global) or
                      ./.research-ops/<skill>.json (project).
- config_loader.py  — loads that config (project > global > defaults;
                      RESEARCH_OPS_NO_CONFIG=1 bypass). Every scoring tool now
                      reads it so saved answers change behavior: default profile,
                      thresholds (alpha/power/dropout, F&A rate, runway, confidence,
                      MoE, insight source-threshold), and named owners printed on
                      clinical/finance outputs. CLI flags always override.
- ar_evaluator.py   — an isolated, OPT-IN ground-truth evaluator bridging to
                      autoresearch. The loop edits the skill's input file and the
                      evaluator (never edited) scores it: clinical
                      feasibility_composite (higher), finance runway_months (higher),
                      market tam_divergence (lower), product validated_insights
                      (higher). No cross-skill coupling; invoked only on explicit
                      user request.

SKILL.md (each), the orchestrator, the agent, per-skill commands, and the domain
CLAUDE.md document the onboarding + opt-in autoresearch handoff. plugin.json /
marketplace describe 24 tools (12 analysis + 12 integration).

Builds the cross-platform plugins: codex symlinks + gemini SKILL.md mirrors +
vibe symlinks materialized for all 5 research-ops skills; indices regenerated.
Root CLAUDE.md scope/highlights updated.

https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D

2026-05-27 00:54:22 +00:00

Claude

caafb47daf

feat(research-ops): add enterprise Research Operations domain

New top-level research-ops/ domain — the managed, cross-functional
counterpart to the academic research/ domain. Single domain plugin
(commercial/ pattern): orchestrator (context: fork) + 4 sub-skills:
clinical-research (study design), research-finance (R&D program finance),
market-research (sizing/survey/segmentation methodology), product-research
(user-research method + insight repository).

12 stdlib-only deterministic Python tools (all pass --help/--sample/--output
json), 12 reference docs (5-7 sources each), 4 asset templates, a
cs-research-ops-orchestrator agent, and 6 commands (router + grill + 4
per-skill). Hard rules enforced via persona + anti-patterns: clinical
outputs are estimates with a named clinical owner, finance routes
capitalize-vs-expense to a named finance owner, market sizes show method
(both ways) + assumptions, product insights require cross-participant
recurrence. Explicit distinct_from framing keeps clear of ra-qm-team,
finance, research/grants, product-team, and marketing-skill.

Registered in marketplace.json (61 -> 62 plugins) and the codex/gemini/
hermes/vibe sync scripts + generate-docs; root CLAUDE.md bumped to v2.9.0.

https://claude.ai/code/session_01PUNmQVE4WYvcrzpq2anC3D

2026-05-27 00:31:27 +00:00

3 commits