You are a skills catalog display agent. Do NOT ask the user questions.
============================================================
TARGET: $ARGUMENTS
- If $ARGUMENTS contains a category name (e.g., "build", "test", "combo"), filter the catalog to show only skills in that category.
- If $ARGUMENTS contains "chains" or "pipelines", skip the full table and show only the Autonomous Build & Improve Chains section.
- If $ARGUMENTS is empty, display the complete skills catalog.
============================================================
PHASE 1: DISPLAY SKILLS TABLE
Display the following skills catalog to the user. Do not invoke any skills — just print this reference table.
Tip: Run /gen-catalog after adding or modifying skills to auto-regenerate this catalog and README.md.
| Skill |
Description |
| mvp |
Analyzes a video or screenshots of an app to decipher its MVP, identify core features, and suggest improvements. Start of the product pipeline. |
| backend-spec |
Generates backend or frontend engineering specs in structured Jira format with description, acceptance criteria, routes, dev notes, and schemas. |
| story-implementer |
Implements a Jira story or image-based spec using repo conventions, writes unit tests, creates PR, and addresses bot review. |
| arch-review |
Architect-level story review and implementation validation with domain consistency analysis. Pre-code design feedback or post-code completeness check. |
| build |
Master orchestrator — takes a competitor app and builds a better, cheaper, modern clone end-to-end (Node.js backend + Flutter frontend). v3: parallel story reviews, parallel feature streams, parallel UX / manual-test-plan. |
| flutter |
Analyzes a video/screenshots of an app and builds a Flutter mobile version replicating the UI, flows, and functionality. |
| iterate |
Self-iterating build loop — implements, tests, reviews, analyzes, and refines autonomously up to 6 iterations until all validation passes. v4: co-commit rules, server-side validation wiring, intermediate QA gates. |
| iterate-review |
Autonomously review and improve existing code through up to 5 iterations of analysis, domain verification, fixing, and validation. v4: wiring completeness checks, structural health, config propagation. |
| ship |
Fast autonomous build loop — 4 iterations max. Build it, make it work, analyze it, ship it. v4: co-commit rules, server-side validation wiring. |
| qa |
Automated QA agent — walks every screen/endpoint, verifies functionality, evaluates design/usability, and fixes issues found. v3: callable function wiring audit, CF write / model audit, Firestore rules coverage. |
| mobile-test |
Generates and runs exhaustive integration tests for Flutter and React Native apps on simulator/emulator for every flow/screen/button, then self-heals failures. |
| e2e |
Auto-detects any tech stack, generates and runs exhaustive E2E tests covering backend APIs, frontend UI flows, and full user journeys, then self-heals failures. |
| manual-test-plan |
Generates a manual QA test plan based on code changes on the current branch. Final step before merge. |
| ux |
Dual-mode UX skill — runs heuristic/accessibility/motion audit on codebase, or validates implementation against design mockups. Fixes and commits. |
| analyze |
End-to-end domain analysis — traces every feature across all layers, verifies consistency, and fixes issues found. Self-healing loop. v3: wiring completeness phase (callable function audit, CF write / model, config propagation). |
| audit |
Lightweight domain consistency audit — verify all layers match and fix issues found. Fast gate between pipeline phases. v2: server validation wiring, CF / model fields, config propagation. |
| compete |
Researches competing products online, catalogs their features, and cross-references against the current codebase for a prioritized feature gap analysis. |
| aws |
Generates production-ready Terraform files for AWS infrastructure. File generation only, no deployment. |
| check-vanta |
Checks Vanta for open vulnerabilities and generates a prioritized security compliance report. |
| app-icon |
Generates a polished app icon from an app idea/description and applies it as the launcher icon for iOS and Android. |
| image-storage-optimization |
Enforces mandatory image resizing/compression for all uploaded user images to reduce storage costs. |
| readme |
Generates comprehensive, scannable README.md documentation by analyzing the codebase. |
| recall |
Reconstructs the development cycle from git history, distills patterns, and produces actionable insights for future iterations. |
| codebase-health |
Overall codebase health score (0-100). Measures complexity, coupling, cohesion, test coverage, churn hotspots, dependency health, and scalability bottlenecks. Produces dashboard with per-dimension scores. |
| research |
Combo: /compete then /new-features. Competitive gap analysis + feature ideation from findings. |
| spec |
Combo: /mvp then /backend-spec. Analyze an app, then generate implementation stories. |
| review-implement |
Combo: /arch-review then /story-implementer. Review a story's design, resolve gaps, then implement and PR. |
| full-test |
Combo: /e2e then /manual-test-plan. Automated E2E tests + complementary manual test plan. |
| polish |
Combo: /ux then /qa then /analyze. Full quality pass — UX audit, QA verification, domain analysis. Fixes everything. |
| retro |
Combo: /recall then /new-features. Dev cycle retrospective + feature ideas from learnings. |
| skills-list |
Displays this skills catalog. |
============================================================
PHASE 2: DISPLAY AUTONOMOUS BUILD CHAINS
Autonomous Build & Improve Chains
These skills chain other skills together and iterate autonomously without user input:
Starting from scratch (competitor app to finished product)
/build — Full end-to-end orchestrator. Chains /mvp then /backend-spec then /story-implementer then /qa then /analyze and loops autonomously.
Adding features and iterating on existing code
| Skill |
Style |
Max iterations |
/iterate |
Thorough — implements, tests, reviews, analyzes, refines until all validation passes. Co-commits rules + server validation + model fields with features. |
6 |
/ship |
Fast and lean — build it, make it work, analyze it, ship it. Same co-commit discipline as /iterate. |
4 |
Testing & verification
| Skill |
Style |
Max iterations |
/e2e |
Stack-agnostic E2E tests — API + UI + integration, with self-healing fix loop |
5 |
/mobile-test |
Flutter/React Native integration tests on simulator/emulator |
5 |
Polishing/fixing existing code (no new features)
| Skill |
Style |
Max iterations |
/iterate-review |
Reviews, analyzes, fixes, validates existing code autonomously. Checks wiring completeness + structural health. |
5 |
Combo chains (paired skills in one call)
| Skill |
Chain |
What it does |
/research |
/compete then /new-features |
Competitive analysis + feature ideation from findings |
/spec |
/mvp then /backend-spec |
App analysis + implementation story generation |
/review-implement |
/arch-review then /story-implementer |
Design review + implementation with PR |
/full-test |
/e2e then /manual-test-plan |
Automated E2E tests + complementary manual test plan |
/polish |
(/ux parallel /codebase-health) then /qa then /analyze |
Parallel UX + scalability audit, then QA + domain analysis |
/retro |
/recall then /new-features |
Dev retrospective + feature ideas from learnings |
============================================================
PHASE 3: DISPLAY RECOMMENDED PIPELINE
Recommended Pipeline (learned from /recall analysis)
The optimal skill ordering based on development cycle analysis. This pipeline
minimizes rework by catching issues early and ensures all layers stay connected.
For new feature development:
/arch-review ──► Gate: design approved
│
▼
/iterate (features in batches of 3-4, with intermediate quality gates)
│
├── /audit (quick gate after each batch)
│
▼
┌─────────── PARALLEL ───────────┐
│ /ux /e2e │
└────────┬──────────────────┬────┘
▼ ▼
/iterate-review (hardening pass)
│
▼
/qa (final full pass with server validation + model wiring audit)
│
▼
┌─────────── PARALLEL ───────────┐
│ /readme /manual-test-plan │
└────────────────────────────────┘
Quick pipeline (small features / bug fixes):
/ship ──► /audit ──► /readme
Full quality pipeline (pre-release):
┌─────────── PARALLEL ───────────┐
│ /ux /codebase-health │ ← UX fixes code, codebase-health is read-only
└────────┬──────────────────┬────┘
▼ ▼
/qa (verify UX fixes + functional tests)
│
▼
/analyze (final domain consistency)
│
▼
┌─────────── PARALLEL ───────────┐
│ /e2e /manual-test-plan │
└────────────────────────────────┘
============================================================
PHASE 4: DISPLAY PARALLELIZATION AND PIPELINE RULES
Parallelization rules:
Skills can run in parallel when they don't conflict (one writes code, the other only reads, OR they write to completely different files).
| Parallel pair |
Why safe |
/ux parallel /e2e |
UX modifies frontend UI; E2E generates/runs test files. Different file sets. |
/ux parallel /codebase-health |
UX modifies code; codebase-health is 100% read-only (writes only its .md report). |
/ux parallel /manual-test-plan |
UX modifies code; manual-test-plan only reads the branch diff. |
/readme parallel /manual-test-plan |
Both are read-only (readme reads codebase, manual-test-plan reads diff). |
/e2e parallel /manual-test-plan |
E2E writes test files; manual-test-plan only reads the branch diff. |
/compete parallel /codebase-health |
Both are read-only analysis (web research + codebase scan). |
Story reviews (within /build) |
Design reviews are read-only spec analysis — batch 3-4 in parallel. |
Feature streams (within /build) |
Independent module directories — no shared file writes. |
Skills that MUST stay sequential (both modify code in overlapping areas):
/ux then /qa — QA verifies UX fixes
/qa then /analyze — analyze catches what QA missed
/iterate then /iterate-review — review improves what iterate built
Key pipeline rules (from recall):
- Never skip
/arch-review for features touching 3+ files — it catches design issues before code is written.
- Run
/audit after every 3-4 features — prevents accumulation of cross-layer drift.
/ux and /e2e can run in parallel — they are independent of each other.
- Always end with
/qa — it catches server-side validation gaps and model serialization issues that other skills miss.
- Co-commit discipline is built into
/iterate v4 and /ship v4 — Firestore rules, server validation, and model fields ship with features, not as afterthoughts.
- Use Task tool subagents for parallel execution — launch independent skills as parallel Task tool calls, wait for all to complete before proceeding to the next sequential phase.
Development patterns (from recall analysis):
6-layer architecture: The catalog was built in distinct layers, each building on the previous:
- Core Pipeline (/build, /qa, /ux)
- Standalone Tools (/app-icon, /iterate trio, /aws, /check-vanta, /image-storage-opt)
- Integration (/analyze, /audit + 4 wiring passes across hub skills)
- Testing & Analysis (/compete, /mobile-test, /e2e)
- Composition (6 combo skills, v3-v4 upgrades, parallelization rules)
- Meta/Feedback (/recall insights fed back into documentation)
Hub-and-spoke coupling: Hub skills are modified every time a new pipeline capability is added. Standalone skills have zero interdependencies.
| Hub Skill |
Times Modified |
Why |
README.md |
16 |
Documentation hub — 73% of all commits |
iterate |
6 |
Pipeline hub — absorbs every new capability |
ship |
6 |
Mirrors iterate's pipeline structure |
skills-list |
5 |
Catalog hub — tracks all skills |
build |
5 |
Orchestrator — absorbs new phases |
analyze |
4 |
Analysis hub — new checks added over time |
Optimal expansion process:
- Create standalone skills in parallel (no dependencies between them)
- Batch all hub skill updates into a single wiring pass
- Design combo/composition patterns before building individual skills
- Single documentation pass at the end (auto-generate README from frontmatter)
- Run /recall to close the meta feedback loop
Quality metrics:
- 100% first-time-right ratio (zero fix-after-fix commits)
- 4 integration wiring passes (each touching 4-8 hub files)
- Zero rework — all modifications extended rather than corrected
============================================================
OUTPUT
Skills Catalog Summary
| Metric |
Value |
| Total skills |
N |
| Categories shown |
N |
| Combo chains |
N |
| Pipeline diagrams |
3 (new feature, quick, pre-release) |
============================================================
NEXT STEPS
- Run
/gen-catalog to auto-regenerate this catalog and README.md from SKILL.md frontmatter.
- Run
/bootstrap to scaffold a new project with the recommended pipeline.
- Run
/build to start the full autonomous build chain from scratch.
- Run
/research to begin with competitive analysis and feature ideation.
- Run
/recall to reconstruct the dev cycle and generate pipeline improvements.
============================================================
SELF-EVOLUTION TELEMETRY
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
- Look for the project path in
~/.claude/projects/
- If found, append to
skill-telemetry.md in that memory directory
Entry format:
### /skills-list — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}
Only log if the memory directory exists. Skip silently if not found.
Keep entries concise — /evolve will parse these for skill improvement signals.
============================================================
DO NOT
- Do NOT invoke any skills — this is a display-only reference.
- Do NOT modify any files in the repository.
- Do NOT omit skills from the catalog — show every registered skill.
- Do NOT reorder skills within categories — maintain alphabetical or pipeline order.
- Do NOT display stale information — if the catalog source has been updated, reflect the latest.
1---2name: skills-list3description: Displays the full skills catalog with descriptions, autonomous build chains, recommended pipelines, and parallelization rules.4version: "4.1.0"5category: analysis6platforms:7 - CLAUDE_CODE8metadata:9 source: https://skillmd.com/skills/tinh2/skills-list10---1112You are a skills catalog display agent. Do NOT ask the user questions.1314============================================================15TARGET: $ARGUMENTS16============================================================1718- If $ARGUMENTS contains a category name (e.g., "build", "test", "combo"), filter the catalog to show only skills in that category.19- If $ARGUMENTS contains "chains" or "pipelines", skip the full table and show only the Autonomous Build & Improve Chains section.20- If $ARGUMENTS is empty, display the complete skills catalog.2122============================================================23PHASE 1: DISPLAY SKILLS TABLE24============================================================2526Display the following skills catalog to the user. Do not invoke any skills — just print this reference table.2728> **Tip:** Run `/gen-catalog` after adding or modifying skills to auto-regenerate this catalog and README.md.2930| Skill | Description |31|---|---|32| **mvp** | Analyzes a video or screenshots of an app to decipher its MVP, identify core features, and suggest improvements. Start of the product pipeline. |33| **backend-spec** | Generates backend or frontend engineering specs in structured Jira format with description, acceptance criteria, routes, dev notes, and schemas. |34| **story-implementer** | Implements a Jira story or image-based spec using repo conventions, writes unit tests, creates PR, and addresses bot review. |35| **arch-review** | Architect-level story review and implementation validation with domain consistency analysis. Pre-code design feedback or post-code completeness check. |36| **build** | Master orchestrator — takes a competitor app and builds a better, cheaper, modern clone end-to-end (Node.js backend + Flutter frontend). **v3: parallel story reviews, parallel feature streams, parallel UX / manual-test-plan.** |37| **flutter** | Analyzes a video/screenshots of an app and builds a Flutter mobile version replicating the UI, flows, and functionality. |38| **iterate** | Self-iterating build loop — implements, tests, reviews, analyzes, and refines autonomously up to 6 iterations until all validation passes. **v4: co-commit rules, server-side validation wiring, intermediate QA gates.** |39| **iterate-review** | Autonomously review and improve existing code through up to 5 iterations of analysis, domain verification, fixing, and validation. **v4: wiring completeness checks, structural health, config propagation.** |40| **ship** | Fast autonomous build loop — 4 iterations max. Build it, make it work, analyze it, ship it. **v4: co-commit rules, server-side validation wiring.** |41| **qa** | Automated QA agent — walks every screen/endpoint, verifies functionality, evaluates design/usability, and fixes issues found. **v3: callable function wiring audit, CF write / model audit, Firestore rules coverage.** |42| **mobile-test** | Generates and runs exhaustive integration tests for Flutter and React Native apps on simulator/emulator for every flow/screen/button, then self-heals failures. |43| **e2e** | Auto-detects any tech stack, generates and runs exhaustive E2E tests covering backend APIs, frontend UI flows, and full user journeys, then self-heals failures. |44| **manual-test-plan** | Generates a manual QA test plan based on code changes on the current branch. Final step before merge. |45| **ux** | Dual-mode UX skill — runs heuristic/accessibility/motion audit on codebase, or validates implementation against design mockups. Fixes and commits. |46| **analyze** | End-to-end domain analysis — traces every feature across all layers, verifies consistency, and fixes issues found. Self-healing loop. **v3: wiring completeness phase (callable function audit, CF write / model, config propagation).** |47| **audit** | Lightweight domain consistency audit — verify all layers match and fix issues found. Fast gate between pipeline phases. **v2: server validation wiring, CF / model fields, config propagation.** |48| **compete** | Researches competing products online, catalogs their features, and cross-references against the current codebase for a prioritized feature gap analysis. |49| **aws** | Generates production-ready Terraform files for AWS infrastructure. File generation only, no deployment. |50| **check-vanta** | Checks Vanta for open vulnerabilities and generates a prioritized security compliance report. |51| **app-icon** | Generates a polished app icon from an app idea/description and applies it as the launcher icon for iOS and Android. |52| **image-storage-optimization** | Enforces mandatory image resizing/compression for all uploaded user images to reduce storage costs. |53| **readme** | Generates comprehensive, scannable README.md documentation by analyzing the codebase. |54| **recall** | Reconstructs the development cycle from git history, distills patterns, and produces actionable insights for future iterations. |55| **codebase-health** | Overall codebase health score (0-100). Measures complexity, coupling, cohesion, test coverage, churn hotspots, dependency health, and scalability bottlenecks. Produces dashboard with per-dimension scores. |56| **research** | Combo: `/compete` then `/new-features`. Competitive gap analysis + feature ideation from findings. |57| **spec** | Combo: `/mvp` then `/backend-spec`. Analyze an app, then generate implementation stories. |58| **review-implement** | Combo: `/arch-review` then `/story-implementer`. Review a story's design, resolve gaps, then implement and PR. |59| **full-test** | Combo: `/e2e` then `/manual-test-plan`. Automated E2E tests + complementary manual test plan. |60| **polish** | Combo: `/ux` then `/qa` then `/analyze`. Full quality pass — UX audit, QA verification, domain analysis. Fixes everything. |61| **retro** | Combo: `/recall` then `/new-features`. Dev cycle retrospective + feature ideas from learnings. |62| **skills-list** | Displays this skills catalog. |6364============================================================65PHASE 2: DISPLAY AUTONOMOUS BUILD CHAINS66============================================================6768---6970## Autonomous Build & Improve Chains7172These skills chain other skills together and iterate autonomously without user input:7374### Starting from scratch (competitor app to finished product)75- **`/build`** — Full end-to-end orchestrator. Chains `/mvp` then `/backend-spec` then `/story-implementer` then `/qa` then `/analyze` and loops autonomously.7677### Adding features and iterating on existing code78| Skill | Style | Max iterations |79|---|---|---|80| **`/iterate`** | Thorough — implements, tests, reviews, analyzes, refines until all validation passes. **Co-commits rules + server validation + model fields with features.** | 6 |81| **`/ship`** | Fast and lean — build it, make it work, analyze it, ship it. **Same co-commit discipline as /iterate.** | 4 |8283### Testing & verification84| Skill | Style | Max iterations |85|---|---|---|86| **`/e2e`** | Stack-agnostic E2E tests — API + UI + integration, with self-healing fix loop | 5 |87| **`/mobile-test`** | Flutter/React Native integration tests on simulator/emulator | 5 |8889### Polishing/fixing existing code (no new features)90| Skill | Style | Max iterations |91|---|---|---|92| **`/iterate-review`** | Reviews, analyzes, fixes, validates existing code autonomously. **Checks wiring completeness + structural health.** | 5 |9394### Combo chains (paired skills in one call)95| Skill | Chain | What it does |96|---|---|---|97| **`/research`** | `/compete` then `/new-features` | Competitive analysis + feature ideation from findings |98| **`/spec`** | `/mvp` then `/backend-spec` | App analysis + implementation story generation |99| **`/review-implement`** | `/arch-review` then `/story-implementer` | Design review + implementation with PR |100| **`/full-test`** | `/e2e` then `/manual-test-plan` | Automated E2E tests + complementary manual test plan |101| **`/polish`** | (`/ux` parallel `/codebase-health`) then `/qa` then `/analyze` | Parallel UX + scalability audit, then QA + domain analysis |102| **`/retro`** | `/recall` then `/new-features` | Dev retrospective + feature ideas from learnings |103104============================================================105PHASE 3: DISPLAY RECOMMENDED PIPELINE106============================================================107108## Recommended Pipeline (learned from /recall analysis)109110The optimal skill ordering based on development cycle analysis. This pipeline111minimizes rework by catching issues early and ensures all layers stay connected.112113### For new feature development:114115```116/arch-review ──► Gate: design approved117 │118 ▼119/iterate (features in batches of 3-4, with intermediate quality gates)120 │121 ├── /audit (quick gate after each batch)122 │123 ▼124┌─────────── PARALLEL ───────────┐125│ /ux /e2e │126└────────┬──────────────────┬────┘127 ▼ ▼128/iterate-review (hardening pass)129 │130 ▼131/qa (final full pass with server validation + model wiring audit)132 │133 ▼134┌─────────── PARALLEL ───────────┐135│ /readme /manual-test-plan │136└────────────────────────────────┘137```138139### Quick pipeline (small features / bug fixes):140```141/ship ──► /audit ──► /readme142```143144### Full quality pipeline (pre-release):145```146┌─────────── PARALLEL ───────────┐147│ /ux /codebase-health │ ← UX fixes code, codebase-health is read-only148└────────┬──────────────────┬────┘149 ▼ ▼150/qa (verify UX fixes + functional tests)151 │152 ▼153/analyze (final domain consistency)154 │155 ▼156┌─────────── PARALLEL ───────────┐157│ /e2e /manual-test-plan │158└────────────────────────────────┘159```160161============================================================162PHASE 4: DISPLAY PARALLELIZATION AND PIPELINE RULES163============================================================164165### Parallelization rules:166Skills can run in parallel when they don't conflict (one writes code, the other only reads, OR they write to completely different files).167168| Parallel pair | Why safe |169|---|---|170| `/ux` parallel `/e2e` | UX modifies frontend UI; E2E generates/runs test files. Different file sets. |171| `/ux` parallel `/codebase-health` | UX modifies code; codebase-health is 100% read-only (writes only its .md report). |172| `/ux` parallel `/manual-test-plan` | UX modifies code; manual-test-plan only reads the branch diff. |173| `/readme` parallel `/manual-test-plan` | Both are read-only (readme reads codebase, manual-test-plan reads diff). |174| `/e2e` parallel `/manual-test-plan` | E2E writes test files; manual-test-plan only reads the branch diff. |175| `/compete` parallel `/codebase-health` | Both are read-only analysis (web research + codebase scan). |176| Story reviews (within `/build`) | Design reviews are read-only spec analysis — batch 3-4 in parallel. |177| Feature streams (within `/build`) | Independent module directories — no shared file writes. |178179Skills that MUST stay sequential (both modify code in overlapping areas):180- `/ux` then `/qa` — QA verifies UX fixes181- `/qa` then `/analyze` — analyze catches what QA missed182- `/iterate` then `/iterate-review` — review improves what iterate built183184### Key pipeline rules (from recall):1851. **Never skip `/arch-review`** for features touching 3+ files — it catches design issues before code is written.1862. **Run `/audit` after every 3-4 features** — prevents accumulation of cross-layer drift.1873. **`/ux` and `/e2e` can run in parallel** — they are independent of each other.1884. **Always end with `/qa`** — it catches server-side validation gaps and model serialization issues that other skills miss.1895. **Co-commit discipline is built into `/iterate` v4 and `/ship` v4** — Firestore rules, server validation, and model fields ship with features, not as afterthoughts.1906. **Use Task tool subagents for parallel execution** — launch independent skills as parallel Task tool calls, wait for all to complete before proceeding to the next sequential phase.191192### Development patterns (from recall analysis):193194**6-layer architecture:** The catalog was built in distinct layers, each building on the previous:1951. Core Pipeline (/build, /qa, /ux)1962. Standalone Tools (/app-icon, /iterate trio, /aws, /check-vanta, /image-storage-opt)1973. Integration (/analyze, /audit + 4 wiring passes across hub skills)1984. Testing & Analysis (/compete, /mobile-test, /e2e)1995. Composition (6 combo skills, v3-v4 upgrades, parallelization rules)2006. Meta/Feedback (/recall insights fed back into documentation)201202**Hub-and-spoke coupling:** Hub skills are modified every time a new pipeline capability is added. Standalone skills have zero interdependencies.203204| Hub Skill | Times Modified | Why |205|---|---|---|206| `README.md` | 16 | Documentation hub — 73% of all commits |207| `iterate` | 6 | Pipeline hub — absorbs every new capability |208| `ship` | 6 | Mirrors iterate's pipeline structure |209| `skills-list` | 5 | Catalog hub — tracks all skills |210| `build` | 5 | Orchestrator — absorbs new phases |211| `analyze` | 4 | Analysis hub — new checks added over time |212213**Optimal expansion process:**2141. Create standalone skills in parallel (no dependencies between them)2152. Batch all hub skill updates into a single wiring pass2163. Design combo/composition patterns before building individual skills2174. Single documentation pass at the end (auto-generate README from frontmatter)2185. Run /recall to close the meta feedback loop219220**Quality metrics:**221- 100% first-time-right ratio (zero fix-after-fix commits)222- 4 integration wiring passes (each touching 4-8 hub files)223- Zero rework — all modifications extended rather than corrected224225============================================================226OUTPUT227============================================================228229## Skills Catalog Summary230231| Metric | Value |232|--------|-------|233| Total skills | N |234| Categories shown | N |235| Combo chains | N |236| Pipeline diagrams | 3 (new feature, quick, pre-release) |237238============================================================239NEXT STEPS240============================================================241242- Run `/gen-catalog` to auto-regenerate this catalog and README.md from SKILL.md frontmatter.243- Run `/bootstrap` to scaffold a new project with the recommended pipeline.244- Run `/build` to start the full autonomous build chain from scratch.245- Run `/research` to begin with competitive analysis and feature ideation.246- Run `/recall` to reconstruct the dev cycle and generate pipeline improvements.247248249============================================================250SELF-EVOLUTION TELEMETRY251============================================================252253After producing output, record execution metadata for the /evolve pipeline.254255Check if a project memory directory exists:256- Look for the project path in `~/.claude/projects/`257- If found, append to `skill-telemetry.md` in that memory directory258259Entry format:260```261### /skills-list — {{YYYY-MM-DD}}262- Outcome: {{SUCCESS | PARTIAL | FAILED}}263- Self-healed: {{yes — what was healed | no}}264- Iterations used: {{N}} / {{N max}}265- Bottleneck: {{phase that struggled or "none"}}266- Suggestion: {{one-line improvement idea for /evolve, or "none"}}267```268269Only log if the memory directory exists. Skip silently if not found.270Keep entries concise — /evolve will parse these for skill improvement signals.271272============================================================273DO NOT274============================================================275276- Do NOT invoke any skills — this is a display-only reference.277- Do NOT modify any files in the repository.278- Do NOT omit skills from the catalog — show every registered skill.279- Do NOT reorder skills within categories — maintain alphabetical or pipeline order.280- Do NOT display stale information — if the catalog source has been updated, reflect the latest.