Skip to content

feat: improve enrichment-module-builder skill score#118

Open
yogesh-tessl wants to merge 1 commit into
SpecterOps:mainfrom
yogesh-tessl:improve/skill-review-optimization
Open

feat: improve enrichment-module-builder skill score#118
yogesh-tessl wants to merge 1 commit into
SpecterOps:mainfrom
yogesh-tessl:improve/skill-review-optimization

Conversation

@yogesh-tessl
Copy link
Copy Markdown

@yogesh-tessl yogesh-tessl commented May 14, 2026

Hey @HarmJ0y 👋

an offensive data enrichment pipeline at nearly 1k stars with its own Slack channel and active community is no small thing. The skills for enrichment module building and package management show you're thinking about how AI agents fit into the security analyst workflow, which is a really practical angle.

ran your skills through tessl skill review at work and found some targeted improvements for enrichment-module-builder. Here's the before/after:

Skill Before After Change
enrichment-module-builder 73% 90% +17%
Changes made to enrichment-module-builder
  • Added explicit "Use when..." clause to the frontmatter description with concrete action verbs (analyzing file formats, selecting parsing libraries, generating YARA rules, creating analyzer code/tests, running E2E integration testing) - this is what pushed the description score from 57% to 100%
  • Condensed gate presentation templates (Steps 2, 3, 4, and 8) from verbose markdown template blocks into concise requirement summaries - same gate behavior, ~75 fewer lines
  • Extracted troubleshooting section into a separate TROUBLESHOOTING.md for progressive disclosure keeps the main skill file focused on the workflow while preserving all DB connection details, container names, and debugging steps
  • All domain-specific content preserved: Nemesis architecture details, code templates, YARA patterns, reference module table, database schema, and integration testing commands are untouched

also stress-tested your enrichment-module-builder skill against a few real-world task evals and it held up really well on scaffolding a YARA-based binary format analyser with the full approval gate workflow. Kudos for that.

quick honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.

if you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.

Hey @HarmJ0y 👋

I ran your skills through `tessl skill review` at work and found some targeted improvements for `enrichment-module-builder`. Here's the full before/after:

| Skill | Before | After | Change |
|-------|--------|-------|--------|
| enrichment-module-builder | 73% | 90% | +17% |
| addressing-dependabot | 90% | — | unchanged |
| managing-packages | 92% | — | unchanged |

<details>
<summary>Changes made to <code>enrichment-module-builder</code></summary>

- **Added explicit "Use when..." clause** to the frontmatter description with concrete action verbs (analyzing file formats, selecting parsing libraries, generating YARA rules, creating analyzer code/tests, running E2E integration testing) — this is what pushed the description score from 57% to 100%
- **Condensed gate presentation templates** (Steps 2, 3, 4, and 8) from verbose markdown template blocks into concise requirement summaries — same gate behavior, ~75 fewer lines
- **Extracted troubleshooting section** into a separate `TROUBLESHOOTING.md` for progressive disclosure — keeps the main skill file focused on the workflow while preserving all DB connection details, container names, and debugging steps
- **All domain-specific content preserved**: Nemesis architecture details, code templates, YARA patterns, reference module table, database schema, and integration testing commands are untouched

</details>

I also stress-tested your `enrichment-module-builder` skill against a few real-world task evals and it held up really well on scaffolding a YARA-based binary format analyzer with the full approval gate workflow. Kudos for that.

Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute.

Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me — [@yogesh-tessl](https://github.com/yogesh-tessl) — if you hit any snags.

Thanks in advance 🙏
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant