Add shanraisshan/draw-json-architecture-skill (0 stars, 1 skill) as the
bottom row of the stars-descending table.
Co-Authored-By: Claude <noreply@anthropic.com>
No drift on tracked dimensions — all 16 frontmatter fields and 5 built-in
agents still match official docs. Version badge only.
Co-Authored-By: Claude <noreply@anthropic.com>
- Bump version to v2.1.158
- Add disallowed-tools frontmatter field (15 -> 16): tools removed from the pool
while skill is active, clears on next message
- Add simplify bundled skill (9 -> 10): cleanup-only review across four parallel
agents; no longer hunts correctness bugs as of v2.1.154 (use /code-review)
Co-Authored-By: Claude <noreply@anthropic.com>
- Bump version to v2.1.158
- Add disableWorkflows, workflowKeywordTriggerEnabled, ultracode (session-only)
to General Settings
- Add teammateDefaultModel (Global config) and pluginSuggestionMarketplaces
(Plugin settings)
- Update opus alias + effortLevel/XHigh notes for Opus 4.8 (latest on Anthropic
API, defaults to high effort, supports xhigh)
- Add CLAUDE_CODE_DISABLE_WORKFLOWS and CLAUDE_CODE_ENABLE_AUTO_MODE env vars
- Remove stale "not yet on official page" note from allowAllClaudeAiMcps
- Refresh Quick Reference example with new workflow keys
Co-Authored-By: Claude <noreply@anthropic.com>
Rename /extra-usage -> /usage-credits, add /share alias to /feedback, add xhigh to effort options; badge -> v2.1.145.
Co-Authored-By: Claude <noreply@anthropic.com>
8 star updates, 4 count updates, 5 ON HOLD count-verify carries (ECC/gstack/BMAD/omc methodology), sort order unchanged.
Co-Authored-By: Claude <noreply@anthropic.com>
Append the v2.1.145 entry recording addition of run, verify, and
run-skill-generator to the official bundled skills table (all COMPLETE).
Co-Authored-By: Claude <noreply@anthropic.com>
Sync to Claude Code v2.1.145: add the three new "Run and verify your app"
bundled skills (run, verify, run-skill-generator), bump official skills
count 6→9, and refresh the Last Updated badge.
Co-Authored-By: Claude <noreply@anthropic.com>
Records the star/count refresh and the K-Dense-AI/VoltAgent sort swap;
all value changes marked RECURRING against prior changelog entries.
Co-Authored-By: Claude <noreply@anthropic.com>
Logs the manual addition of alirezarezvani/claude-skills as row 8, the
floor-lowering precedent (21k → ~15k), and the cross-model classification
note (candidate for CROSS-MODEL WORKFLOWS in future review).
Co-Authored-By: Claude <noreply@anthropic.com>
Insert alirezarezvani/claude-skills at row 8 of SKILL COLLECTIONS table
(after K-Dense-AI/scientific-agent-skills 21k). 246 skills across 9
domains; cross-tool repo supporting Claude Code, Codex, Gemini CLI,
Cursor + 8 more. Drops empirical SKILL COLLECTIONS star floor from 21k
to ~15k — precedent-setting. Refresh badge to May 13, 2026 1:28 AM PKT.
Co-Authored-By: Claude <noreply@anthropic.com>
Updates the read-only research agent so it detects (rather than
generates) prose in the CONCEPTS Description column. Description
Accuracy check now explicitly flags sentence-style summaries; Return
Format and critical rule #8 require recommended Description values to
contain badges + links only.
Co-Authored-By: Claude <noreply@anthropic.com>
Updates the executor command so future drift runs never reintroduce
prose into the CONCEPTS table Description column. Adds explicit
guidance in Phase 2 (Missing Concepts spec), Phase 3 (row template
now shows badge syntax), and as new critical rule #14.
Co-Authored-By: Claude <noreply@anthropic.com>
- Goal row: add [![Implemented]] badge pointing to new implementation/claude-goal-implementation.md
- Hot table convention is badges + links only; remove drifted prose
descriptions from Deep Links, Agent View, and Goal rows so all rows
conform to the same shape
Co-Authored-By: Claude <noreply@anthropic.com>
Embeds two X.com screenshots (Alex Finn, Meta Alchemist) with verbatim
tweet text and source URLs. Covers two patterns: asking the agent to
propose its own /goals, and asking it to draft a /goal prompt from
session + repo context.
Co-Authored-By: Claude <noreply@anthropic.com>
Establish changelog/cross-model-workflows/changelog.md mirroring the
structure of skill-collections and development-workflows changelogs.
Initial entry documents section creation, the 4 included repos, the
10k+ stars threshold policy, EveryInc/compound-engineering-plugin
exclusion (verified Claude-only), and a sub-threshold watchlist
(decolua/9_router 9.3k, 1rgs/claude-code-proxy 4k, jamubc/gemini-mcp-tool 2k,
LLM-Red-Team/kimi-cc 2k, jarrodwatts/claude-delegator 1k).
Co-Authored-By: Claude <noreply@anthropic.com>
Insert new section between DEVELOPMENT WORKFLOWS and SKILL COLLECTIONS.
Seeds the table with musistudio/claude-code-router (34k Router),
router-for-me/CLIProxyAPI (32k Router), openai/codex-plugin-cc (18k
Plugin), and BeehiveInnovations/pal-mcp-server (12k MCP, formerly
zen-mcp-server). Re-home the existing Cross-Model methodology doc as
the section intro and drop the now-redundant bullet from Others.
Co-Authored-By: Claude <noreply@anthropic.com>
Record the manual addition of pbakaus/impeccable (27k stars, 1 SKILL.md
with 7 domain references) into the SKILL COLLECTIONS table — mirrors the
2026-05-01 entry pattern used when addyosmani/agent-skills was added.
Co-Authored-By: Claude <noreply@anthropic.com>
Insert pbakaus/impeccable at row 4 of SKILL COLLECTIONS table (between
wshobson/agents 35k and addyosmani/agent-skills 27k). Note 1 SKILL.md
with 7 design domain references. Refresh badge to May 13, 2026 12:10 AM PKT.
Co-Authored-By: Claude <noreply@anthropic.com>
Records second v2.1.138 audit run within the day. README CONCEPTS table
unchanged between runs (no commits touched lines 22–68). Findings entirely
INVALID or ON HOLD: 1 spurious drift claim verified false (Tasks `/tasks`
command is real per claude-commands.md:75); 6 RECURRING-INVALID findings
re-flagged per durable user policy (platform surfaces, SDK-scoped pages,
sibling beta inconsistency); 1 ON HOLD (Voice Dictation page no longer
reads as beta but tag persists conservatively); 4 verifications COMPLETE.
No CONCEPTS table edits applied.
Co-Authored-By: Claude <noreply@anthropic.com>
Same-day timestamp refresh after the second concepts drift workflow run.
No table content changes — version still v2.1.138.
Co-Authored-By: Claude <noreply@anthropic.com>
One HIGH COMPLETE (badge bumped to v2.1.138 / May 09 2026 7:02 PM PKT). Four
ON HOLD (worktree.baseRef, parentSettingsBehavior, --plugin-url, hard_deny —
deferred as compact rows or admin-tier fields not warranting CONCEPTS surface).
Eight INVALID (recurring-style /slash-commands redirect, missing standalone
rows for Output Styles/Sandboxing/Permission Modes/Headless/etc, Effort Levels,
Workflows row critique — all per established user policy). Five LOW
verifications confirmed all 35+ external URLs and 21 local file paths still
resolve.
Co-Authored-By: Claude <noreply@anthropic.com>
All 16 frontmatter fields and 5 built-in agents match across the 12-version
window (v2.1.126 → v2.1.138). No add/remove changes to subagent surfaces.
Co-Authored-By: Claude <noreply@anthropic.com>
Frontmatter fields (15) and bundled skills (6) fully synchronized with official
docs across the v2.1.126 → v2.1.138 window. No actionable drift.
Co-Authored-By: Claude <noreply@anthropic.com>
Records four COMPLETE actions: 1 HIGH (added /radio at Config #12, count
75→76 with renumbering), 3 MED (signature refinements for /clear [name],
/review [PR], /context [all]).
Co-Authored-By: Claude <noreply@anthropic.com>
Records msitarzewski/agency-agents 185→186 oscillation as INVALID (within ±1
margin per prior 184–186 oscillation policy; per-directory enumeration sums to
172 vs Python crawl's 186, agent confidence 0.93). VoltAgent 144 confirmed as
real (per-category sum exact, prior 144↔145 oscillation resolved as content
change rather than pagination artifact). Star counts unchanged
(msitarzewski 95k, VoltAgent 19k); sort order preserved.
Co-Authored-By: Claude <noreply@anthropic.com>
Shayan RaisandClaude
