CtrlK
BlogDocsLog inGet started
Tessl Logo

refine

End-of-session reflection. Reviews friction encountered during the session and proposes updates to docs/ to capture lessons learned.

61

Quality

72%

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 ./.agents/skills/refine/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A concise, actionable, well-structured instruction-only skill whose only real gap is the absence of an explicit validation checkpoint in its workflow.

Suggestions

Insert a verification step before applying edits, e.g., 'Re-read the changed docs/ lines to confirm they are accurate and minimal before reporting.'

Add a checkpoint after identifying friction to confirm each item is genuinely session-confirmed before proposing an update.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: a single concrete command, bulleted friction categories, and tight rules with no padding or explanation of concepts Claude already knows.

3 / 3

Actionability

It gives an executable command ('git diff main...HEAD --stat'), specific doc paths to read, concrete friction categories, and a clear 'add only what would have saved time this session' directive — copy-paste ready guidance.

3 / 3

Workflow Clarity

The five steps are clearly sequenced, but there is no explicit validation/verification checkpoint (e.g., confirming a proposed doc update is accurate before applying it); the report step is a summary, not a feedback loop.

2 / 3

Progressive Disclosure

Under 50 lines with no external references needed; the Instructions and Rules sections are well-organized, satisfying the simple-skill allowance for a top score without bundle files.

3 / 3

Total

11

/

12

Passed

Description

57%

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 clear and reasonably specific about a distinctive niche, but it lacks an explicit 'Use when...' trigger clause, which caps completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause such as 'Use at the end of a session when the user asks to reflect, capture lessons learned, or update docs based on what went wrong.'

Broaden the action list to be more comprehensive (e.g., 'reviews friction, updates docs/, flags missing validation rules, and records new codebase patterns').

Include natural user phrasings like 'lessons learned', 'what went wrong', 'update the docs' as trigger terms.

DimensionReasoningScore

Specificity

Names concrete actions ('Reviews friction encountered during the session and proposes updates to docs/'), but only two actions and lacks the breadth of the 3-anchor example which lists several specific operations.

2 / 3

Completeness

It states clearly what the skill does, but the 'when' is only implied by 'End-of-session'; the rubric caps completeness at 2 when an explicit 'Use when...' trigger clause is missing.

2 / 3

Trigger Term Quality

Terms like 'friction', 'lessons learned', and 'end-of-session reflection' are somewhat natural, but there is no explicit 'Use when...' clause enumerating common user phrasings, leaving coverage of natural variations incomplete.

2 / 3

Distinctiveness Conflict Risk

The niche of end-of-session friction review directed at docs/ is distinctive and unlikely to be confused with other skills' triggers.

3 / 3

Total

9

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
windmill-labs/windmill
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.