CtrlK
BlogDocsLog inGet started
Tessl Logo

optimize-skill

Use when iteratively optimizing an existing SKILL.md (or a skill folder with bundle files) — runs a Tessl-gated Ralph loop with snapshot-and-revert protection, never accepts a worse `tessl review run` score, and stops when no candidate change improves both the score and the structural quality. Triggers for `/optimize-skill PATH`, "make this skill better", "iterate on this SKILL.md", "improve this skill's tessl score".

77

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

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

The content is a tight, highly actionable optimization workflow with explicit sequencing and validation gates, scoring at the top on conciseness, actionability, and workflow clarity. Its only real defect is the missing `REFERENCE.md` bundle file, which the skill references but does not ship.

Suggestions

Ship the referenced `REFERENCE.md` (sibling file) in the skill bundle, or remove the two 'read REFERENCE.md' references — as-is they violate the skill's own G4 gate (every cross-file reference points to an extant file).

Replace the editorial framing lines (e.g. 'the author has the worst judgment of their own work', 'aesthetic intuition is not') with the concrete rule they imply, to trim residual commentary.

Reconcile the data-flow block's '+ tessl + jq + bc installed' with the body, which deliberately uses awk to avoid a bc dependency — pick one and drop the stale bc mention.

DimensionReasoningScore

Conciseness

The body is lean and tactical — executable bash, a flowchart, an ROI table, and a hard-gate table — and explicitly avoids over-explaining concepts Claude already knows ('The Tessl judge is the umpire; aesthetic intuition is not'), with a small amount of editorial color that does not pad it into verbosity.

3 / 3

Actionability

Provides copy-paste-ready, executable commands — the jq score-extraction pipeline, rsync snapshot/revert, awk numeric comparison — plus concrete CLI flags and version notes (tessl 0.87, `--workspace`, `.review.reviewScore`), matching the fully-executable anchor.

3 / 3

Workflow Clarity

A clearly sequenced process (parse→validate→recall→baseline→iterate→spec-review→retain) with a mermaid flowchart and an acceptance-criteria table (G1–G6) defining explicit validation checkpoints and revert feedback loops ('Any failure → revert that iteration').

3 / 3

Progressive Disclosure

The body is structured as an overview that defers detail to a sibling `REFERENCE.md`, referenced twice and clearly signaled, but `REFERENCE.md` is not present in the bundle — the one-level-deep reference points to a non-existent file (a G4 violation the skill itself defines), so it cannot earn the clear-navigation anchor of 3.

2 / 3

Total

11

/

12

Passed

Description

100%

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 is a strong, third-person trigger description that names concrete capabilities, lists natural user trigger phrases, answers both what and when, and occupies a clearly distinct niche. No meaningful weaknesses against the rubric.

DimensionReasoningScore

Specificity

Names multiple concrete mechanisms — 'Tessl-gated Ralph loop with snapshot-and-revert protection', 'never accepts a worse `tessl review run` score', 'stops when no candidate change improves both the score and the structural quality' — rather than vague single actions.

3 / 3

Completeness

Opens with 'Use when iteratively optimizing...' (the when) and states the loop/never-regress behavior (the what), so both questions are explicitly answered with explicit triggers — not merely implied.

3 / 3

Trigger Term Quality

Explicit 'Triggers for `/optimize-skill PATH`, "make this skill better", "iterate on this SKILL.md", "improve this skill's tessl score"' gives natural phrasings a user would actually say, matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The Tessl-gated skill-optimization niche with its own slash-command and specific trigger phrases is highly distinct and unlikely to fire for an unrelated skill.

3 / 3

Total

12

/

12

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
AndreJorgeLopes/proof-of-skill
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.