common-architecture-di…
Draw architecture diagrams as editable draw.io files with a fixed house style, C4 levels, and evidence-tagged shapes. Use when producing a system context,…
Pre-write audit for skill violations: checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart/TS code or editing SKILL.md files with active project skills. Load as composite; on auto-fixed violation, also load
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill common-feedback-reporter --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/common-feedback-reporterContext preview
The summary Claude sees to decide when to auto-load this skill.
Pre-write audit for skill violations: checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart/TS code or editing SKILL.md files with active project skills. Load as composite; on auto-fixed violation, also load
name: common-feedback-reporter
description: "Pre-write audit for skill violations: checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart/TS code or editing SKILL.md files with active project skills. Load as composite; on auto-fixed violation, also load +common/common-learning-log."
metadata:
triggers:
files:
- "SKILL.md"
- "**/*.dart"
- "**/*.ts"
- "**/*.tsx"
- "+common/common-learning-log"
keywords:
- skill violation
- pre-write audit
- audit violationsFor any request that writes code or edits `SKILL.md`, treat the requested change as a planned write. Before showing code, run this audit and emit the complete violation block when a loaded skill rule is violated. The block must include these exact labels: `SKILL VIOLATION DETECTED`, `Auto-fixed`, `Root Cause`, `User Intent`, and `Skill Gap`. Then apply the fix and show the corrected result. Do not silently produce the violating implementation, and do not replace the required block with a summary.
Apply the same contract to these cases:
For the oversized-draft case, include this exact sentence pattern before the rewrite: `SKILL.md is 100+ lines; extract large examples to references/. Root Cause: ... User Intent: ... Skill Gap: ...`.
**Quick check before `write_to_file`, `replace_file_content`, `multi_replace_file_content`:**
1. **Check** - Any skills loaded for this file extension?
2. **Audit** - planned code violate loaded skill rules?
When violation detected, output this block before fixing:
🚨 SKILL VIOLATION DETECTED Skill: [skill-id] File: [relative/path/to/file.ext]:[line-range] Rule: [exact rule text from SKILL.md] Violation: [what planned code does — up to 5-line offending snippet] Fix: [corrected approach — up to 5-line corrected snippet] Auto-fixed: YES / NO Root Cause: [AMBIGUOUS_RULE | MISSING_COVERAGE | OUTDATED_GUIDANCE | COMPETING_RULES | PATTERN_MISMATCH] User Intent: [1 sentence: what the user was trying to achieve] Skill Gap: [1–2 sentences: what change to the SKILL.md would prevent this next time] Co-skills: [other active skill IDs, comma-separated, or 'none']
| Code | When to use | | ------------------- | ---------------------------------------------------- | | `AMBIGUOUS_RULE` | Rule wording permits multiple interpretations | | `MISSING_COVERAGE` | Common pattern not addressed anywhere in skill | | `OUTDATED_GUIDANCE` | Skill references deprecated API or framework version | | `COMPETING_RULES` | Two loaded skills gave contradictory guidance | | `PATTERN_MISMATCH` | AI misread or misapplied anti-pattern definition |
Then apply fix immediately — not wait for user confirmation.
Before `notify_user` or task completion:
** I write code?** YES → ** I audit skills?** NO → Audit now
Use report labels `SKILL VIOLATION DETECTED`, `Auto-fixed`, `Root Cause`, `User Intent`, and `Skill Gap`; move oversized examples to `references/`.
The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.
Repo: hoangnguyen0403/agent-skills-standard
Draw architecture diagrams as editable draw.io files with a fixed house style, C4 levels, and evidence-tagged shapes. Use when producing a system context,…
Enforce SOLID principles, guard-clause style, function size limits, and intention-revealing naming across all languages. Use when refactoring for readability,…
Standardize BRD and BRD-lite discovery for business goals, stakeholder impact, current-to-future state, and measurable value outcomes. Use when creating BRD,…
Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback.
Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are…
Standardize dynamic application security testing for backend APIs, frontend web apps, and mobile clients. Covers ZAP, Nuclei, Nikto, sqlmap, ffuf, browser…