Skills Audit Documentation Progressive-disclosure design pattern for ALAI skill system. Pillar #4 — Skills Audit Overview Pillar #4 — Skills Audit Overview Date: 2026-05-04 MC: #99131 Phase: DESIGN + PoC (Phase 2) Spec: agentic-os-pillar4-skills-audit-2026-05-04.md Executive Summary This audit covers the ALAI skill system progressive-disclosure refactor: 79 skills inventoried, top-20 refactor priorities identified, L0-L3 rubric established, and PoC analysis completed for task-postflight skill. Key Findings 79 active skill directories on disk; 94 rows in skill-registry.db (32 phantoms, 17 unregistered) Only 15 skills have any log invocations in the 19-day measurement window mehanik (186 hits) and update-config (1 hit) appear in logs but have no disk directory — ghost invocations 9 skills with references/ dir; 70 are monolithic (L0/L1) 12 TOB skills have nested structure — invisible to Claude Code flat-discovery loader Highest-priority refactor target: task-postflight (5,367 tokens × 21 measured invocations = priority_score 82.05) Reality anchor: At current ALAI scale (Claude Max flat-rate subscription), context-bloat incremental cost is approximately $0-2/month. The value of this audit is context window capacity management , not dollar cost reduction. Inventory Summary Metric Value Source Active skill dirs on disk 79 ls ~/.claude/skills/ | grep -v _archived | wc -l Archived skills 32 ls ~/.claude/skills/_archived/ | wc -l skill-registry.db rows 94 sqlite3 skill-registry.db 'SELECT COUNT(*) FROM skills;' DB-only phantoms 32 comm comparison Disk-only unregistered 17 comm comparison Skills with references/ dir 9 find query Skills with invocations in window 15 log grep Measurement window 19 days 2026-04-16 to 2026-05-05 Total invocations in window 267 awk filter Ghost invocations (mehanik) 186 log grep — mehanik not on disk Aggregate Savings Projection Skills loaded per turn Tokens saved vs. baseline % context window recovered (128K window) Only task-postflight (PASS path) 3,500 tokens 2.7% task-postflight + prompt-forge 4,700 tokens 3.7% Top-5 hot-path skills (ranks 1-5) 7,300 tokens 5.7% All top-20 (max benefit, full session) 19,500 tokens 15.2% All 79 skills at L3 (theoretical max) ~35,000 tokens 27.3% Assumes 40-50% body-token reduction per skill post-refactor. These are per-turn estimates derived from body-token reduction; monthly projections without measured session counts would be phantom claims. Related Documentation Skills Inventory: Top 20 Priority table with per-skill triage L0-L3 Design Pattern: Progressive-disclosure rubric and anti-pattern catalog PoC Analysis: task-postflight refactor demonstration (541 → 194 LOC, 64.7% reduction) Source spec: ~/system/specs/agentic-os-pillar4-skills-audit-2026-05-04.md (479 lines) HiveMind record: TBD MC: #99131 (ready_for_review) Skills Inventory — Top 20 Priority Skills Inventory — Top 20 Priority Measurement window: 19 days (2026-04-16 to 2026-05-05) Priority formula: log10(skill_md_tokens_est) * (1 + invocations_30d) Top-20 Refactor Priority Table Rank Skill Name LOC Tokens Inv 30d Est $/mo (current) Est $/mo (post-L3) Savings $/mo Priority Score Owner 1 task-postflight 541 5,367 21 $0.547 $0.078 $0.469 82.054 john 2 prompt-forge 224 2,372 20 $0.350 $0.070 $0.280 70.877 john 3 plan-with-team 140 1,177 13 $0.105 $0.042 $0.063 42.991 john 4 build-plan 90 923 7 $0.126 $0.063 $0.063 23.722 john 5 ask-board 307 2,623 3 $0.125 $0.038 $0.087 13.675 john 6 build 79 838 3 $0.113 $0.057 $0.056 11.693 john 7 sentinel 105 990 2 $0.116 $0.058 $0.058 8.987 john 8 sync 46 346 2 $0.087 $0.087 $0.000 7.617 john 9 learning-opportunity 165 1,433 1 $0.067 $0.034 $0.033 6.313 john 10 vault-unlock 117 1,312 1 $0.142 $0.071 $0.071 6.236 john 11 incident-response 122 1,051 1 $0.067 $0.034 $0.033 6.043 john 12 youtube-learning 93 877 1 $0.136 $0.068 $0.068 5.886 john 13 code-review 87 674 1 $0.002 $0.001 $0.001 5.657 john 14 lightrag-upload 87 659 1 $0.117 $0.059 $0.058 5.638 john 15 lightrag-status 101 625 1 $0.121 $0.061 $0.060 5.592 john 16 product-lifecycle 491 5,103 0 $0.081 $0.041 $0.040 3.708 john 17 skill-creator 362 4,911 0 $0.088 $0.044 $0.044 3.691 john 18 doc-coauthoring 375 4,274 0 $0.208 $0.104 $0.104 3.631 john 19 mcp-builder 236 2,457 0 $0.135 $0.068 $0.067 3.390 john 20 plan-build-test 293 2,437 0 $0.099 $0.050 $0.049 3.387 john est_$/mo (post-L3) = estimate assuming 50% body-token reduction via progressive disclosure Per-Skill Triage — Top 5 #1 task-postflight Current footprint: 541 LOC / 5,367 tokens Why bloated: BLOAT_LOC_GT_300 — Contains anomaly decision tree (Section 3), learning-opportunity dispatch template (Section 4), memory writer procedure (Section 5), and failure mode reference table (Section 8) all inline in one file. Most of this content is only needed after an anomaly is detected. Recommended action: Split — progressive-disclose. Trigger skeleton ≤200 LOC stays in SKILL.md; Sections 3-5+8 move to references/. Predicted savings: ~3,500 tokens/session on typical PASS flows (63% context reduction); full 5,367 tokens only loaded on ANOMALY path. #2 prompt-forge Current footprint: 224 LOC / 2,372 tokens Why bloated: Single references/agent-briefs.md exists but body still contains full 5-panelist dispatch protocol, model tier assignments, and synthesis rules inline. Recommended action: Split — move per-panelist briefs and synthesis rules to references/; keep trigger condition and dispatch skeleton in core. Predicted savings: ~1,200 tokens/session (50% reduction). #3 plan-with-team Current footprint: 140 LOC / 1,177 tokens Why bloated: No references/ dir. Builder/validator role descriptions, round-robin protocol, and output templates are all inline. Frequently invoked (13x in window). Recommended action: Progressive-disclose — move builder brief and validator brief to references/. Keep selection logic in SKILL.md. Predicted savings: ~700 tokens/session (59% reduction) across 13 monthly invocations. #4 build-plan Current footprint: 90 LOC / 923 tokens Why bloated: No references/ dir. Moderate size but high invocation frequency (7x). Output templates and TaskList format examples inline. Recommended action: Progressive-disclose — move TaskList format examples and edge-case handling to references/quick-ref.md. Predicted savings: ~400 tokens/session (43% reduction). #5 ask-board Current footprint: 307 LOC / 2,623 tokens Why bloated: BLOAT_LOC_GT_300 — 5-agent dispatch briefs are fully inline. Each panelist persona description (50-80 lines each) loads for every board invocation. Recommended action: Split — move per-panelist briefs to references/panelist-.md. Keep dispatch skeleton (trigger, model tier, synthesis format) in SKILL.md. Predicted savings: ~1,800 tokens/session (69% reduction). Full per-skill triage for all 20: See main audit spec ~/system/specs/agentic-os-pillar4-skills-audit-2026-05-04.md §4. CSV inventory: ~/system/specs/agentic-os-pillar4-skills-inventory.csv (79 skills, 20 columns)