opencode-skills-collection 3.0.3 → 3.0.5

package/bundled-skills/linear-claude-skill/SKILL.md

@@ -48,12 +48,6 @@ linear issues list
 
 ---
 
-
-## When to Use This Skill
-
-Manage Linear issues, projects, and teams
-
-Use this skill when working with manage linear issues, projects, and teams.
 ## 🔐 Security: Varlock Integration
 
 **CRITICAL**: Never expose API keys in terminal output or Claude's context.
@@ -174,12 +168,6 @@ See [Project Management Commands](#project-management-commands) for full referen
 
 ---
 
-
-## When to Use This Skill
-
-Manage Linear issues, projects, and teams
-
-Use this skill when working with manage linear issues, projects, and teams.
 ## Project Planning Workflow
 
 ### Create Issues in the Correct Project from the Start
@@ -326,12 +314,6 @@ npx tsx scripts/linear-ops.ts link-initiative "Phase 11" "Q2 Goals"
 
 ---
 
-
-## When to Use This Skill
-
-Manage Linear issues, projects, and teams
-
-Use this skill when working with manage linear issues, projects, and teams.
 ## Tool Selection
 
 Choose the right tool for the task:
@@ -506,12 +488,6 @@ npx tsx scripts/linear-ops.ts unlink-initiative "Phase X" "Old Initiative"
 
 ---
 
-
-## When to Use This Skill
-
-Manage Linear issues, projects, and teams
-
-Use this skill when working with manage linear issues, projects, and teams.
 ## Sync Patterns (Bulk Operations)
 
 For bulk synchronization of code changes to Linear, see **sync.md**.

package/bundled-skills/linkedin-cli/SKILL.md

@@ -35,7 +35,7 @@ Once the user provides the tokens, run:
 linkedin setup --linked-api-token=TOKEN --identification-token=TOKEN
 ```
 
-## When to Use
+### When to Use
 Use this skill when you need to **orchestrate LinkedIn actions from scripts or an AI agent** instead of clicking through the web UI:
 
 - Building outreach, research, or recruiting workflows that rely on LinkedIn data and messaging.

package/bundled-skills/logistics-exception-management/SKILL.md

@@ -195,7 +195,7 @@ Track these metrics weekly and trend monthly:
 - For the comprehensive edge case library with full analysis, see [edge-cases.md](references/edge-cases.md)
 - For complete communication templates with variables and tone guidance, see [communication-templates.md](references/communication-templates.md)
 
-## When to Use
+### When to Use
 Use this skill when you need to **triage and resolve logistics exceptions or design exception-handling playbooks**:
 
 - Handling delays, damages, shortages, misdeliveries, and claims across LTL, FTL, parcel, intermodal, ocean, or air.

package/bundled-skills/matematico-tao/SKILL.md

@@ -340,34 +340,34 @@ StateFlow como processo reativo S = (State, Ev
 
 ```
 
-## 1. Estrutura Formal
+### 1. Estrutura Formal
 
 [Definição matemática do componente]
 
-## 2. Invariantes Identificados
+### 2. Invariantes Identificados
 
 1. INV-01: [invariante em notação matemática ou pseudocódigo formal]
 2. INV-02: ...
 
-## 3. Propriedades Verificadas
+### 3. Propriedades Verificadas
 
 ✅ [Propriedade que foi verificada como correta + argumento]
 ⚠️  [Propriedade suspeita + evidência]
 ❌ [Violação encontrada + contra-exemplo]
 
-## 4. Análise De Complexidade
+### 4. Análise De Complexidade
 
 - Tempo: O(?) com argumento
 - Espaço: O(?) com argumento
 - Caso médio: Θ(?) com análise probabilística se relevante
 
-## 5. Riscos Matemáticos Prioritizados
+### 5. Riscos Matemáticos Prioritizados
 
 | Rank | Risco | Severidade | P(ocorrência) | Score |
 |------|-------|-----------|--------------|-------|
 | 1 | ... | 9/10 | 0.8 | 7.2 |
 
-## 6. Recomendações Provadas
+### 6. Recomendações Provadas
 
 #### R-01: [Título]
 **Argumento**: [Por que matematicamente esta mudança é correta]

package/bundled-skills/mental-health-analyzer/SKILL.md

@@ -714,7 +714,7 @@ source: community
 2. 冥想 - 有效率85% ✓
 3. 深呼吸 - 有效率75% ✓
 
-## 建议
+### 建议
 - 下午工作压力大时，可使用深呼吸或短暂散步
 - 保持规律运动，对情绪改善效果显著
 - 改善睡眠有助于减轻焦虑和疲劳

package/bundled-skills/multi-advisor/SKILL.md

@@ -57,7 +57,7 @@ A sintese dessas perspectivas e o que separa decisoes mediocres de decisoes imor
 
 ---
 
-## 2.1 Personas Disponiveis
+### 2.1 Personas Disponiveis
 
 | Agente | Especialidade Core | Quando Chamar |
 |--------|-------------------|---------------|
@@ -75,7 +75,7 @@ A sintese dessas perspectivas e o que separa decisoes mediocres de decisoes imor
 | `007` | Security, threat modeling, infraestrutura | Riscos de seguranca, vulnerabilidades |
 | `product-inventor` | Design systems, UX/UI, React/Next.js | Execucao de produto, UI engineering |
 
-## 2.2 Boards Pre-Configurados
+### 2.2 Boards Pre-Configurados
 
 | Board | Composicao | Uso |
 |-------|-----------|-----|
@@ -89,7 +89,7 @@ A sintese dessas perspectivas e o que separa decisoes mediocres de decisoes imor
 
 ---
 
-## 3.1 Fluxo Standard
+### 3.1 Fluxo Standard
 
 ```
 1. RECEBER: Questao do usuario
@@ -100,7 +100,7 @@ A sintese dessas perspectivas e o que separa decisoes mediocres de decisoes imor
 6. SINTETIZAR: Visao consolidada + recomendacao final
 ```
 
-## 3.2 Como Invocar Cada Persona
+### 3.2 Como Invocar Cada Persona
 
 Para cada membro do board, adote completamente a perspectiva daquela persona:
 
@@ -131,7 +131,7 @@ Para cada membro do board, adote completamente a perspectiva daquela persona:
 
 ---
 
-## 4.1 Estrutura Do Conselho
+### 4.1 Estrutura Do Conselho
 
 ```markdown
 
@@ -216,7 +216,7 @@ Board: AI_BOARD (Sam + Karpathy + LeCun + Ilya)
 
 ---
 
-## 6. Regras Do Board
+## 2. Regras Do Board
 
 1. **Autenticidade** — Cada persona fala com sua voz unica. Jobs nao fala como Buffett.
 2. **Tensao e saudavel** — Se todo board concorda, investigar mais fundo.
@@ -227,7 +227,7 @@ Board: AI_BOARD (Sam + Karpathy + LeCun + Ilya)
 
 ---
 
-## 7. Consulta Customizada
+## 3. Consulta Customizada
 
 Usuario pode customizar o board:
 
@@ -244,7 +244,7 @@ Usuario pode customizar o board:
 
 ---
 
-## 8. Integracao Com Ecossistema
+## 4. Integracao Com Ecossistema
 
 Esta skill usa as personas instaladas no ecossistema:
 - Ao consultar cada persona, adotar sua perspectiva COMPLETA (nao superficial)

package/bundled-skills/nestjs-expert/SKILL.md

@@ -11,7 +11,7 @@ date_added: "2026-02-27"
 
 You are an expert in Nest.js with deep knowledge of enterprise-grade Node.js application architecture, dependency injection patterns, decorators, middleware, guards, interceptors, pipes, testing strategies, database integration, and authentication systems.
 
-## When invoked:
+### When invoked:
 
 0. If a more specialized expert fits better, recommend switching and stop:
    - Pure TypeScript type issues → typescript-type-expert

package/bundled-skills/nodejs-best-practices/SKILL.md

@@ -301,7 +301,7 @@ node --test src/**/*.test.ts
 
 ---
 
-## 10. Anti-Patterns to Avoid
+## 9. Anti-Patterns to Avoid
 
 ### ❌ DON'T:
 - Use Express for new edge projects (use Hono)
@@ -322,7 +322,7 @@ node --test src/**/*.test.ts
 
 ---
 
-## 11. Decision Checklist
+## 10. Decision Checklist
 
 Before implementing:
 

package/bundled-skills/postgres-best-practices/SKILL.md

@@ -54,7 +54,7 @@ Each rule file contains:
 
 For the complete guide with all rules expanded: `AGENTS.md`
 
-## When to Use
+### When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
 
 ## Limitations

package/bundled-skills/prisma-expert/SKILL.md

@@ -10,7 +10,7 @@ date_added: "2026-02-27"
 
 You are an expert in Prisma ORM with deep knowledge of schema design, migrations, query optimization, relations modeling, and database operations across PostgreSQL, MySQL, and SQLite.
 
-## When Invoked
+### When Invoked
 
 ### Step 0: Recommend Specialist and Stop
 If the issue is specifically about:

package/bundled-skills/product-inventor/SKILL.md

@@ -45,7 +45,7 @@ Product Inventor e Design Alchemist de nivel maximo — combina Product Thinking
 
 ---
 
-## 1.1 Os Cinco Principios Inegociaveis
+### 1.1 Os Cinco Principios Inegociaveis
 
 **PRINCIPIO 1 — SIMPLICIDADE RADICAL**
 Remova tudo que nao e essencial. Nao ha premio por complexidade.
@@ -83,7 +83,7 @@ Novidade real raramente vem de invencao total. Vem de:
 - fluxo viciante (que cria habito sem esforco)
 - execucao impecavel (que elimina toda friccao)
 
-## 1.2 O Que Nunca Fazer
+### 1.2 O Que Nunca Fazer
 
 - UI generica. "Parece qualquer outro app" e morte.
 - Dashboard padrao com 12 cards sem hierarquia.
@@ -95,7 +95,7 @@ Novidade real raramente vem de invencao total. Vem de:
 
 ---
 
-## 2.1 Motor 1 — "First Principles Ui"
+### 2.1 Motor 1 — "First Principles Ui"
 
 Antes de qualquer pixel, decomponha o produto em atomos:
 
@@ -127,7 +127,7 @@ PROXIMO PASSO INEVITAVEL
 
 Use esse framework para cada tela, nao so para o produto inteiro.
 
-## 2.2 Motor 2 — "Killer Interaction" (Interacao Assinatura)
+### 2.2 Motor 2 — "Killer Interaction" (Interacao Assinatura)
 
 Todo produto memoravel tem 1 interacao que e sua assinatura.
 Nao e gimmick. E a solucao mais elegante para o problema central.
@@ -157,7 +157,7 @@ Passo 5: Pergunte: "E se o usuario nao precisasse clicar em nada?"
 - Pode virar demo de 10 segundos que impressiona? ✓
 - E difícil de copiar sem entender a logica por tras? ✓
 
-## 2.3 Motor 3 — "Design System Proprietario"
+### 2.3 Motor 3 — "Design System Proprietario"
 
 Nunca use tokens genericos. Todo produto precisa de identidade propria.
 

package/bundled-skills/production-audit/SKILL.md

@@ -0,0 +1,209 @@
+---
+name: production-audit
+description: "Audit a shipped repo for production-readiness gaps across RLS, webhooks, secrets, grants, Stripe idempotency, mobile UX, and deployment health."
+category: security
+risk: safe
+source: community
+source_repo: commitshow/production-audit
+source_type: community
+date_added: "2026-05-04"
+author: commitshow
+tags: [security, audit, production, vibe-coding, rls, webhook, stripe, supabase, mobile]
+tools: [claude, cursor, gemini, codex, antigravity]
+license: "MIT"
+license_source: "https://github.com/commitshow/production-audit/blob/main/LICENSE"
+---
+
+# Production Audit
+
+## Overview
+
+A skill that runs an external audit on a shipped repo's deployed state — live URL, GitHub signals, secrets exposure, RLS gaps, webhook idempotency, indexes, observability, prompt injection, and ten other failure modes that AI-assisted projects routinely miss.
+
+This is **complementary** to in-session security skills (`security-review`, OWASP-style, VibeSec, Trail of Bits). Those scan the editor buffer at write-time. This scans the deployed product after you commit. Different timing, different inputs, different findings. Run both for serious launches.
+
+The skill wraps the [commit.show](https://commit.show) audit engine via the public CLI (`npx commitshow audit . --json`). Stable JSON envelope (`schema_version: "1"`, additive-only). Writes a `.commitshow/audit.{md,json}` sidecar so future agent sessions can read prior state without re-running the engine.
+
+## When to Use This Skill
+
+- Use when the user asks "is this production-ready", "what would break in prod", "score my project", "what did I miss", "audit my repo", "ready to ship".
+- Use right after merging a feature branch to `main` (helpful as a pre-deploy gate).
+- Use before a public launch / Show HN post / investor demo.
+- Use when `git log` shows >20 commits since the last `.commitshow/audit.md` was written.
+
+### Skip when
+
+- During active in-session coding — use `security-review` / OWASP-style for line-level patterns. This skill is for post-merge / pre-ship review.
+- For library / scaffold-form repos — the engine handles **app form** best; libraries get a partial-substitute score.
+- If `.commitshow/audit.json` already exists and is < 1 hour old, read that instead of re-running. Audit is rate-limited (anonymous: 20/IP/day · 5/repo/day · 2000/day global).
+- Inside a private / non-GitHub repo — the audit pulls public GitHub signals, so private repos return a `not_found` error.
+
+## How It Works
+
+### Step 1: Run the audit
+
+From the repo root. The CLI is pinned to a known-good range (an attacker-pushed `0.4.x` won't be picked up silently — bumping the floor is a deliberate edit), the sidecar directory is created up-front, and stderr is split off so install/deprecation warnings can't corrupt the JSON envelope:
+
+```bash
+mkdir -p .commitshow
+npx commitshow@^0.3.23 audit . --json \
+  > .commitshow/audit.json \
+  2> .commitshow/audit.stderr.log
+```
+
+This also writes a human-readable `.commitshow/audit.md` next to it. Subsequent invocations should diff against the prior `audit.json` if it exists, so you can lead with "+5 since yesterday's audit" instead of just an absolute number.
+
+If the user pointed at a remote URL instead of `.`, swap `.` for the URL — keep the same `mkdir -p` + version pin + stderr split:
+
+```bash
+mkdir -p .commitshow
+npx commitshow@^0.3.23 audit github.com/owner/repo --json \
+  > .commitshow/audit.json \
+  2> .commitshow/audit.stderr.log
+```
+
+### Step 2: Parse the envelope
+
+The JSON envelope is stable (`schema_version: "1"`, additive-only). Read these fields:
+
+| Field | Meaning |
+|---|---|
+| `score.total` | 0-100 production-readiness score |
+| `score.delta_since_last` | change vs. parent snapshot · positive = improving |
+| `score.band` | `strong` (80+) · `mid` (60-79) · `early` (<60) |
+| `concerns[]` | top issues, ordered by impact · each has `axis` + `bullet` |
+| `strengths[]` | top 3 things that work · for context only |
+| `standing` | optional · only when the project is auditioning on commit.show |
+| `snapshot.created_at` / `trigger_type` | when the audit ran |
+
+Concerns are sorted by decision-impact, not severity. Position 1 is the bullet to lead with.
+
+### Step 3: Surface to the user
+
+Lead with score + trajectory in **one sentence**, then the top concerns. Do not dump the full JSON. Format:
+
+```
+Score: 82/100 (+5 since yesterday) · band: strong
+
+Top concerns:
+  ↓ [Security] No API rate limiting on /auth — IP cap missing
+  ↓ [Infrastructure] webhook handler at api/stripe.ts — signature verified, but no
+    idempotency-key check (replay attack window open)
+
+Want me to fix the webhook idempotency gap first?
+```
+
+Rules:
+- Use the exact bullet from `concerns[].bullet` — the audit engine already wrote action-oriented copy.
+- Don't list strengths unless the user explicitly asks. They're not actionable in this context.
+- Always end with a follow-up question that names a specific concern. Don't ask "what do you want to do?" — ask "fix X first?".
+- If `score.delta_since_last` is negative or null, lead with the absolute score only.
+
+### Step 4: If the user picks a concern, scope a fix
+
+For the chosen concern:
+1. Read the file(s) cited in the bullet.
+2. Confirm the gap matches the description (the engine occasionally over-flags when the issue is mitigated elsewhere).
+3. Propose a minimal patch — single-file when possible.
+4. **Don't apply without explicit approval.** Show the diff first. The user is deciding what to ship; you're a lens.
+
+After applying a fix, suggest re-running with `--refresh` (same canonical form as Step 1, so `audit.json` stays the source of truth for delta calculations):
+
+```bash
+mkdir -p .commitshow
+npx commitshow@^0.3.23 audit . --json --refresh \
+  > .commitshow/audit.json \
+  2> .commitshow/audit.stderr.log
+```
+
+## Examples
+
+### Example 1: User asks "is this production-ready?"
+
+```bash
+mkdir -p .commitshow
+npx commitshow@^0.3.23 audit . --json \
+  > .commitshow/audit.json \
+  2> .commitshow/audit.stderr.log
+```
+
+Then surface:
+
+```
+Score: 67/100 · band: mid
+
+Top concerns:
+  ↓ [Security] members table uses column-level GRANT but paid_audits_credit
+    column lacks SELECT grant — silent 42501 on every read
+  ↓ [Infrastructure] stripe.checkout.sessions.create called without
+    idempotencyKey — duplicate-charge surface
+
+Want me to fix the column GRANT first? Single SQL line.
+```
+
+### Example 2: Cross-check a specific concern
+
+User: "show me where the webhook idempotency gap is"
+
+```bash
+cat .commitshow/audit.json | jq '.concerns[] | select(.axis=="Infrastructure")'
+```
+
+Find the file path in the bullet, read it, confirm the gap matches.
+
+## Best Practices
+
+- ✅ Always cite the exact bullet from `concerns[].bullet` — they're already action-oriented
+- ✅ Lead with score + delta in a single sentence, then concerns
+- ✅ End with a specific follow-up question naming a concern
+- ✅ Read prior `.commitshow/audit.json` before re-running (within 1h)
+- ✅ Use `--refresh` after the user merges a fix so the next audit reflects it
+- ❌ Don't dump full JSON to the user
+- ❌ Don't list strengths unless the user explicitly asks
+- ❌ Don't apply fixes without approval — show diff first
+- ❌ Don't fault private repos for not auditing — explain why and suggest making public
+
+## Limitations
+
+- This skill does not replace environment-specific validation, testing, or expert review.
+- The audit engine is calibrated for **deployed apps** with a live URL. CLI / library / scaffold form gets a partial-substitute score (max ~45/50 on the audit pillar) — fair but not flattering.
+- Behind a corporate firewall blocking `*.supabase.co`, the API call fails. There is no offline mode — the audit relies on the public engine.
+- Cold audit takes 60-90s. Cached audits (within 7 days) return instantly. `--refresh` force-bypasses cache (counts against rate limits).
+
+## Security & Safety Notes
+
+- The skill executes `npx commitshow@latest audit ...` which is a network call to a public API at `https://api.commit.show` (proxied to Supabase Edge Functions). No credentials are sent — anonymous usage subject to per-IP / per-URL / global rate limits.
+- The CLI writes `.commitshow/audit.{md,json}` in the current working directory. These files are safe to commit (no secrets) but conventionally gitignored as transient artifacts.
+- The audit engine **only reads** public GitHub signals. It does not modify the user's repo or push commits.
+- All per-finding fix proposals must be shown as diffs and approved by the user before any edit. Never apply without explicit confirmation.
+
+## Common Pitfalls
+
+- **Problem:** Audit returns `not_found` for a private repo
+  **Solution:** The engine pulls public GitHub signals only. Either make the repo public or use `--no-network` for local-only deterministic checks.
+
+- **Problem:** Rate limit hit (`429`)
+  **Solution:** Wait until next day (limits reset 00:00 UTC) or sign in at commit.show for higher per-repo caps.
+
+- **Problem:** Score seems too low for a polished library / CLI
+  **Solution:** The engine biases toward app form. CLI / library / scaffold gets a partial substitute score capped around 45/50 on the audit pillar. Calibration acknowledged trade-off.
+
+- **Problem:** `concerns[]` is empty after re-running
+  **Solution:** Re-audit may have hit cache. Use `--refresh` to force-bypass.
+
+## Related Skills
+
+- `@security-review` — In-session line-level security patterns. Run alongside this skill, not in place of.
+- `@vibesec` — Editor-buffer security review for vibe-coded projects. Different lens.
+- `@owasp-security` — OWASP Top 10 coverage during coding. Companion.
+- `@trail-of-bits-skills` — CodeQL / Semgrep static analysis. Different layer.
+
+## Additional Resources
+
+- Canonical repo: <https://github.com/commitshow/production-audit>
+- Audit engine source: <https://github.com/commitshow/commitshow/blob/main/supabase/functions/analyze-project/index.ts>
+- 14-frame failure framework documented in the engine source above.
+- JSON schema: stable at `schema_version: "1"` · additive-only changes.
+- CLI: <https://github.com/commitshow/cli>
+- Public REST API: `https://api.commit.show/audit?repo=...&format=json`
+- skills.sh listing: <https://skills.sh/commitshow/production-audit>

package/bundled-skills/production-scheduling/SKILL.md

@@ -206,7 +206,7 @@ Track per shift and trend weekly:
 - For the comprehensive edge case library with full resolution playbooks, see [edge-cases.md](references/edge-cases.md)
 - For complete communication templates with variables and tone guidance, see [communication-templates.md](references/communication-templates.md)
 
-## When to Use
+### When to Use
 Use this skill when you need to **design or adjust production schedules and constraint‑focused execution plans**:
 
 - Sequencing jobs, balancing lines, and optimising changeovers in discrete or batch manufacturing.

package/bundled-skills/quality-nonconformance/SKILL.md

@@ -227,7 +227,7 @@ Track these metrics weekly and trend monthly:
 - For the comprehensive edge case library with full analysis, see [edge-cases.md](references/edge-cases.md)
 - For complete communication templates with variables and tone guidance, see [communication-templates.md](references/communication-templates.md)
 
-## When to Use
+### When to Use
 Use this skill when you need to **run or improve non‑conformance and CAPA processes in regulated manufacturing**:
 
 - Investigating NCRs, selecting root‑cause methods, and defining MRB dispositions and CAPA actions.

package/bundled-skills/react-best-practices/SKILL.md

@@ -122,7 +122,7 @@ Each rule file contains:
 
 For the complete guide with all rules expanded: `AGENTS.md`
 
-## When to Use
+### When to Use
 This skill is applicable to execute the workflow or actions described in the overview.
 
 ## Limitations

package/bundled-skills/react-patterns/SKILL.md

@@ -197,6 +197,14 @@ date_added: "2026-02-27"
 
 ---
 
+## 11. File Structure
+
+<img width="1150" height="1438" alt="image" src="https://github.com/user-attachments/assets/10369698-472c-4695-a494-2c0672103aa1" />
+
+Use this image as a reference for a better file structure of the project
+
+---
+
 > **Remember:** React is about composition. Build small, combine thoughtfully.
 
 ## When to Use

package/bundled-skills/recursive-context-pruning-token-budgeting/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: recursive-context-pruning-token-budgeting
+description: "Optimizes AI agent performance by pruning redundant context, managing token usage, and enforcing ultra-concise, direct-to-value responses."
+category: prompt-engineering
+risk: safe
+source: self
+source_repo: Kench001/antigravity-awesome-skills
+source_type: self
+date_added: "2026-05-03"
+author: Kench001
+tags: [efficiency, token-optimization, brevity, context-management]
+tools: [claude, cursor, gemini]
+# Optional: declare the upstream license if source_repo is set
+# license: "MIT"
+# license_source: "https://github.com/owner/repo/blob/main/LICENSE"
+---
+
+# Recursive Context Pruning & Token Budgeting
+
+## Overview
+
+This skill implements a "Gatekeeper" logic to prevent context window bloat and unnecessary token expenditure. It ensures the agent only processes relevant data shards and adheres to an Atomic Precision protocol—delivering functional answers with zero conversational filler. By recursively summarizing state and stripping "bridge phrases," it maximizes the longevity and speed of long-running development workflows.
+
+## When to Use This Skill
+
+- Use when building multi-step agents to prevent repetition and "memory drift" in long conversations.
+- Use when working with large document sets or codebases to avoid dumping entire files into the prompt.
+- Use when you need purely functional output (code/logic) without "Sure! Here is your..." intros.
+
+## How It Works
+
+### Step 1: Metadata Sharding
+
+Scan the available data for headers, summaries, and key indicators. Create a "map" of the context rather than injecting the full source. Never pull the entire file into the prompt unless a specific, narrowed fragment is requested.
+
+### Step 2: Token Budget Allocation
+
+Calculate a "Safe Response Limit" based on the current context window. Allocate 30% for current logic processing, 20% for immediate output, and 50% for a future context buffer.
+
+### Step 3: Atomic Output Filtering
+
+Strip all "Bridge Phrases" (e.g., "I've updated the code," "Based on your request," "Sure"). Start the response immediately with the solution or the code block.
+
+### Step 4: Ambiguity Check
+
+Before executing Step 3, scan for missing critical variables (e.g., specific file names or environment types). If the prompt is too ambiguous, bypass the atomic output and generate exactly one concise question to resolve the blocker.
+
+### Step 5: Abstractive Compression
+
+Summarize the current turn into a "compressed state string" (e.g., `[Project: Feasify | State: Auth-Fixed | Remaining-Tasks: 2]`) to discard redundant conversational data before the next prompt.
+
+## Examples
+
+### Example 1: Filtered Code Output (No Filler)
+
+```text
+User: "Update the Firebase config to use environment variables."
+```
+
+```javascript
+const firebaseConfig = {
+  apiKey: process.env.VITE_FIREBASE_API_KEY,
+  authDomain: process.env.VITE_FIREBASE_AUTH_DOMAIN,
+  projectId: process.env.VITE_FIREBASE_PROJECT_ID
+};
+```
+
+### Example 2: Essential Clarification
+
+```text
+User: "Deploy the function."
+```
+
+```text
+"Specify environment: production or staging?"
+```
+
+## Best Practices
+
+- ✅ **Direct Start:** Place the code or answer at the very first character of the response.
+- ✅ **Summarize-as-you-go:** Turn 10 pages of discussion into 5 bullet points for the next turn.
+- ✅ **Omit Signatures:** Never end with "Let me know if you need more help."
+- ❌ **No Bridge Phrases:** Avoid "Here is the code," "Sure," or "I can help with that."
+- ❌ **No Guessing:** If input is missing, ask immediately rather than wasting tokens on a generic guess.
+
+## Limitations
+
+- This skill does not replace environment-specific validation, testing, or expert review.
+- Extreme brevity can occasionally hide important nuances; use concise inline comments (`// crucial step`) for critical notes.
+
+## Security & Safety Notes
+
+- Never prune safety headers, environment-specific security constraints, or system-level instructions during the compression stage.
+- Maintain original system instructions at the "Root" of the context to prevent context-loss-based jailbreaks.
+
+## Common Pitfalls
+
+- **Problem:** The response is so brief it lacks the context needed for implementation.
+  **Solution:** Use concise inline code comments instead of separate paragraphs of text.
+
+- **Problem:** The agent loses the overarching goal due to over-compression.
+  **Solution:** Always pin the "Primary Objective" to the top of every pruned prompt.
+
+## Related Skills
+
+- `@atomic-precision-response` - Specifically for removing conversational filler.
+- `@context-sharding` - For managing large-scale documentation mapping.
+

package/bundled-skills/rehabilitation-analyzer/SKILL.md

@@ -599,7 +599,7 @@ source: community
 - 用药与训练强度的关系
 - 疼痛控制与用药依从性
 
-## 使用示例
+### 使用示例
 
 ### 场景1：新用户开始康复
 ```

package/bundled-skills/returns-reverse-logistics/SKILL.md

@@ -208,7 +208,7 @@ Level 1 (Returns Associate) → Level 2 (Team Lead, 2 hours) → Level 3 (Return
 - For the comprehensive edge case library with full analysis, see [edge-cases.md](references/edge-cases.md)
 - For complete communication templates with variables and tone guidance, see [communication-templates.md](references/communication-templates.md)
 
-## When to Use
+### When to Use
 Use this skill when you need to **design, improve, or troubleshoot returns and reverse logistics operations**:
 
 - Defining or revising returns policies, grading standards, and disposition routes across channels.