Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentnpx agentmods add skills/matrixfounder/agentic-development/skill-enhancerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/matrixfounder/agentic-development/skill-enhancer)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/skill-enhancer"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/skill-enhancer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/skill-enhancer"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/skill-enhancer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.02610 |
| Opus 5.5 | $0.00010 | $0.01044 |
| Sonnet 5.5 | $0.00005 | $0.00522 |
| Haiku 4.5 | $0.00003 | $0.00261 |
Grade B, and why
skill-enhancer scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- **Security Remediation**: Fix vulnerabilities flagged by `skill-validator` (e.g., `curl | bash`, secrets, weak permissions). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Security Remediation**: Fix vulnerabilities flagged by `skill-validator` (e.g., `curl | bash`, secrets, weak permissions). How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Enhancer
Purpose: This meta-skill analyzes other skills for compliance with TDD, CSO, and Script-First standards, guiding the agent through upgrades.
1. Red Flags (Anti-Rationalization)
STOP and READ THIS if you are thinking:
- "I'll just add the sections blindly" -> WRONG. You must understand why the skill fails before fixing it.
- "The description is close enough" -> WRONG. It must start with "Use when".
- "Examples are optional" -> WRONG. "Rich Skills" mandate examples.
- "It's just a small 20-line example" -> WRONG. Inline blocks > 12 lines are prohibited. Extract them.
- "I'll instruct the agent to parse the file line-by-line in text" -> WRONG. Use "Script-First".
2. Capabilities
- Audit: Detect gaps (missing Red Flags, oversized inline blocks, poor CSO, weak language) using
analyze_gaps.py. - Rule scoping: the analyser reads prose, not code. Fenced blocks and inline
code spans are masked before the prose rules run,
[--flag VALUE]is CLI usage notation rather than an unfilled slot, and/tmp/out.pdfin a reproducible command is not the absolute-path anti-pattern — only a path naming one machine or one user's account is (WI-033). - Execution Policy Audit: Detect missing
Execution Mode,Script Contract,Safety Boundaries, andValidation Evidencesections. - Security Remediation: Fix vulnerabilities flagged by
skill-validator(e.g.,curl | bash, secrets, weak permissions). - Plan: Propose specific content improvements using
references/refactoring_patterns.md. - Execute: Apply refactoring patterns to upgrade the skill.
2.5. Execution Mode
- Mode:
hybrid - Rationale: gap triage and refactoring decisions are prompt-driven, while gap detection is script-driven.
2.6. Script Contract
- Primary Command:
python3 scripts/analyze_gaps.py <target-skill-path> [--json] [--strict] - Inputs: target skill path + optional output mode.
- Outputs: two lists and a status —
gaps(blocking) andadvisories(reported, non-blocking). - Failure Semantics: non-zero exit when blocking gaps exist (deterministic
gate behavior). Advisories are printed and leave the exit code at 0;
--strictpromotes them to blocking. The split mirrorsvalidate_skill.py, which already passes a skill that has only warnings — without it the two gates return different verdicts on the same file (WI-033). - Advisory classes:
[Language](the graduated-wording call is per instruction, not mechanical) and[Execution Policy](a declared warning-first migration), plus the minor tier of[Token Efficiency].
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/usage_example.md 3.8 KB
- references/refactoring_patterns.md 3.1 KB
- references/security_refactoring.md 2.4 KB
- references/testing-skills-with-subagents.md 12 KB
- references/vdd_checklist.md 2.4 KB
- references/writing_skills_best_practices_anthropic.md 40 KB
- scripts/.keep 0 B
- scripts/analyze_gaps.py 34 KB runs code
- scripts/skill_standards_default.yaml 1.9 KB
- scripts/skill_utils.py 23 KB runs code
- scripts/tests/__init__.py 0 B runs code
- scripts/tests/test_human_channel.py 21 KB runs code
- scripts/tests/test_rule_scoping.py 31 KB runs code
- scripts/tests/test_stdout_broken_pipe.py 4.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +18 lines c5c523124168
- 1mo ago First seen · 150 lines · 25 tokens per session scan B f2417392b5a8
skill-enhancer is a skill published in the GitHub repository MatrixFounder/Agentic-development (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 2,610 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
workflow
Perform any development work on the ambient-ui component. Full workflow instructions.
compliance-check
Run a Maestro-style regulatory compliance review for GDPR/CCPA, cookie consent, data handling, and licensing.
chimera-write-the-check-before-the-code
A criterion written after the implementation describes the implementation. Write the failing check first, watch it fail, then build.
Learn what defines effective BDD scenarios
Interactive guidance on writing complete, effective BDD scenarios for story-flow.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.