CtrlK
BlogDocsLog inGet started
Tessl Logo

ac-insight-extractor

Extract insights from autonomous coding sessions. Use when learning from completions, extracting patterns, analyzing decisions, or improving future performance.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ac-insight-extractor/SKILL.md

The canonical home for this skill is ac-insight-extractor in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with executable starter code and a clean one-level reference, but the workflow lacks validation checkpoints around its batch apply step. Strong progressive disclosure and conciseness, moderate workflow rigor.

Suggestions

Add an explicit validation/checkpoint step after `apply_learnings` (e.g. confirm which insights were applied and verify `insights.json` was written) to satisfy the batch-operation feedback-loop requirement.

Make the Quick Start snippet self-contained by defining `project_dir` (e.g. `project_dir = Path('.')`) and noting the async requirement, closing the minor actionability gaps.

Trim the redundant Purpose/intro lines that restate the frontmatter description to push conciseness to fully lean.

DimensionReasoningScore

Conciseness

The body is lean with a short Purpose, a Quick Start code block, and a one-line API pointer; the only trimming opportunity is the Purpose/intro restating the frontmatter description, so it sits just below the maximally lean 5 anchor.

4 / 5

Actionability

Quick Start gives concrete, executable code importing the real module and calling real methods that match the script, with only minor gaps (undefined `project_dir` placeholder, async context assumed) and the API reference deferred entirely to the script file.

4 / 5

Workflow Clarity

A clear 3-step sequence is present (instantiate, extract, apply), but there are no validation or verification checkpoints; because `apply_learnings` is a batch-style operation that mutates state and writes to disk, the missing-feedback-loop cap holds it at 3.

3 / 5

Progressive Disclosure

The body is short (~25 lines), well-organized into Purpose/Quick Start/API Reference sections, and makes a clearly signaled one-level-deep reference to a real file (`scripts/insight_extractor.py`, which exists), matching the simple-skill top anchor.

5 / 5

Total

16

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description cleanly answers both what and when with explicit trigger guidance and a distinct niche, with only the capability list being somewhat generic. It is well above the midpoint on every dimension.

DimensionReasoningScore

Specificity

It names the domain ('autonomous coding sessions') and one concrete action ('Extract insights'), but the stated capability is generic rather than a comprehensive list of specific actions, matching the 'domain + 1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

It explicitly answers both what ('Extract insights from autonomous coding sessions') and when ('Use when learning from completions, extracting patterns, analyzing decisions, or improving future performance') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

The 'Use when' clause lists several natural trigger phrases ('learning from completions, extracting patterns, analyzing decisions, or improving future performance') giving good keyword coverage, though it lacks synonyms/file-extension-style variants that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

The 'autonomous coding sessions' niche is specific and distinct, but as a meta-level analysis/learning skill it has minor overlap risk with other code-analysis or reflection skills, fitting 'mostly distinct; minor overlap risk' better than the clear-niche 5 anchor.

4 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
fernandezbaptiste/Skrillz
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.