CtrlK
BlogDocsLog inGet started
Tessl Logo

update-skills

Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.

72

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The content is highly actionable with concrete paths, commands, and templates, and the multi-step workflow is clearly sequenced with a quality-check checkpoint. Its only weakness is mild verbosity in the intro and decision sections, which could be tightened to better respect the token budget.

Suggestions

Trim the opening paragraph that restates the description; the 'When to Use' section already covers the triggers.

Condense the 'Decision: Skill vs Instruction vs Learning' bullets so the decision criteria are scannable rather than prose-heavy.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but the opening paragraph restates the description and the "Decision: Skill vs Instruction vs Learning" section is prose-heavy with explanatory clauses that could be tightened, matching the score-2 anchor of mostly efficient with some unnecessary explanation.

2 / 3

Actionability

It provides concrete, copy-paste-ready guidance: exact file paths (`.github/skills/{name}/SKILL.md`), executable shell snippets (`ls`, `grep -r`), and complete frontmatter templates for both skills and instructions.

3 / 3

Workflow Clarity

The procedure is clearly sequenced (1. Identify → 2. Check existing → 3a/3b/3c → 4. Quality Checks → 5. Inform) with an explicit validation checkpoint via the "Quality Checks" section that gates saving.

3 / 3

Progressive Disclosure

The skill is self-contained with no bundle files and is organized into well-signaled sections (## When to Use, ## Decision, ## Procedure with numbered subsections, ## Quality Checks), so per the simple-skill guidance well-organized sections without external references earn a 3.

3 / 3

Total

11

/

12

Passed

Description

90%

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 clearly states what the skill does and gives strong, natural trigger guidance including the literal "learn!" phrase. It is concise, third-person, and unlikely to conflict with other skills; its only weakness is that the listed actions are somewhat high-level rather than enumerating several concrete operations.

DimensionReasoningScore

Specificity

It names concrete actions ("Create or update repository skills and instructions") but the actions stay at a fairly high level rather than enumerating multiple specific operations, matching the score-2 anchor that names the domain and some actions without being comprehensive.

2 / 3

Completeness

It explicitly answers both halves: what ("Create or update repository skills and instructions") and when ("Use when the user says 'learn!', when a significant pattern or pitfall is identified..."), with explicit trigger guidance.

3 / 3

Trigger Term Quality

It surfaces natural terms a user would actually say — notably the literal trigger "learn!" plus "significant pattern or pitfall" and "reusable domain knowledge" — giving good coverage of natural invocation phrasing.

3 / 3

Distinctiveness Conflict Risk

The niche — persisting session learnings as skills/instructions — is distinct, and the "learn!" trigger plus "captured for future sessions" framing make it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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
posit-dev/positron
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.