CtrlK
BlogDocsLog inGet started
Tessl Logo

learn

Distill a reusable skill from anything — a directory, a URL, pasted notes, or what you just did together — or refine an existing skill with new learnings. Use when the user says '/learn', 'learn this', 'turn this into a skill', 'capture this workflow', 'make a skill from <source>', or 'improve/update the <name> skill'. Produces or updates a .claude/skills/<name>/SKILL.md authored to NanoClaw's skill guidelines. (This CREATES or REFINES a skill from a source; it does not install existing skills from a registry.)

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

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-structured, instruction-only meta-skill with a clear numbered workflow, concrete tool guidance, and explicit verification in the placement step. Main weakness is mild redundancy between the opening paragraph, 'When to use', and the description, plus a missing full worked output example.

Suggestions

Trim the redundancy between the opening paragraph and the 'When to use' list, since both restate the source types and invocations already in the frontmatter description.

Add one small complete example of a resulting SKILL.md (frontmatter plus a few body lines) so the authoring step has a copy-paste-ready reference rather than only a frontmatter template.

Make the step-5 validation unconditional — e.g. always confirm the folder name matches the frontmatter and the YAML parses — rather than gating the dry-run on 'if feasible'.

DimensionReasoningScore

Conciseness

The body is mostly lean procedural guidance that assumes Claude's competence and avoids explaining basic concepts, but the opening paragraph and 'When to use' section repeat trigger/source information already in the description, which could be trimmed. Not a 5 because of this noticeable redundancy; not a 3 because the bulk is efficient and non-padded.

4 / 5

Actionability

Gives concrete, executable guidance — naming specific tools ('Glob the structure, Read the key files, Grep', 'WebFetch the page'), a YAML frontmatter template, and a worked Example — so Claude knows exactly what to do. Not a 5 because there is no complete finished SKILL.md example to copy, only the frontmatter template; not a 3 because the steps are specific and actionable rather than pseudocode.

4 / 5

Workflow Clarity

A clearly numbered five-step workflow (Identify → Gather → Distill → Author → Place and verify) with explicit verification in step 5 ('confirm the folder name matches... and the YAML parses', 'dry-run the procedure... to confirm it is correct') and a defined refine branch. Not a 5 because the dry-run validation is conditional ('If feasible') and checkpoints are otherwise implicit; not a 3 because validation steps are present.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear sections (When to use, Workflow, Example, Notes) and an inlined, one-level reference to docs/skill-guidelines.md rather than nested deferrals; no bundle files are needed. Not a 5 because the skill exceeds the under-50-line simple-skill exception and the docs/skill-guidelines.md pointer is informational rather than a clearly signaled navigation aid.

4 / 5

Total

16

/

20

Passed

Description

100%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.

A strong, third-person description that concretely states what the skill does, lists multiple natural trigger phrases, and explicitly distinguishes creating/refining skills from installing them. Both the 'what' and 'when' are answered with concrete, low-conflict triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Distill a reusable skill from anything', 'refine an existing skill with new learnings', 'Produces or updates a .claude/skills/<name>/SKILL.md' — across several named source types (directory, URL, notes, conversation), giving comprehensive coverage. It is not a 4 because coverage of actions and sources is exhaustive rather than having minor gaps.

5 / 5

Completeness

Explicitly answers both what ('Distill a reusable skill... or refine an existing skill... Produces or updates a .claude/skills/<name>/SKILL.md') and when ('Use when the user says...') with concrete trigger phrases. Not a 4 because both what and when are concrete and explicit rather than one being only weakly specified.

5 / 5

Trigger Term Quality

Includes a comprehensive set of natural phrases users would actually say — '/learn', 'learn this', 'turn this into a skill', 'capture this workflow', 'make a skill from <source>', 'improve/update the <name> skill' — covering synonyms and variations. Not a 4 because the trigger list is broad and natural rather than missing common terms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (creating/refining skills) and explicitly disambiguates from a neighboring task — 'it does not install existing skills from a registry' — minimizing conflict risk. Not a 4 because the boundary is explicitly stated rather than only mostly distinct.

5 / 5

Total

20

/

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
nanocoai/nanoclaw
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.