CtrlK
BlogDocsLog inGet started
Tessl Logo

custody-recognition

Use when a source may entrust work. Not for casual mentions, terminal offers, generic planning, or Schedule/Needs Me. Output: abstain, admit, offer, or retry.

64

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/custody-recognition/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 lean, well-structured instruction-only skill with concrete tool calls, explicit validation checkpoints, and clear branching. The only gap is the absence of a complete worked call example, which would lift actionability from 4 to 5.

DimensionReasoningScore

Conciseness

Instruction-dense with no concept over-explanation; the slight repetition of the 'do not re-offer / do not create a Task' guardrail across sections is the only trimming opportunity, keeping it just below 5.

4 / 5

Actionability

Names concrete tool calls (cat_cafe_admit_entrusted_work, cat_cafe_offer_custody, cat_cafe_retry_custody_admission) with specific fields and branches; falls short of 5 only because no complete copy-paste call example is shown.

4 / 5

Workflow Clarity

Clear sequence (read source state, choose branch, completion check) with explicit validation (verify admitted/resumed plus owner ref/revision/receipt) and feedback loops for conflict/stale-source rereads and needs_clarification retry.

5 / 5

Progressive Disclosure

A single self-contained policy file with no external references needed, organized into clear headed sections (read first, branches, clarification, completion) for easy navigation and no nested references.

5 / 5

Total

18

/

20

Passed

Description

71%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 tight, well-bounded description that answers what and when while actively disambiguating itself from adjacent skills. Its main weakness is trigger-term quality: the natural phrases users would say are isolated in the triggers field rather than surfaced in the description.

Suggestions

Fold one or two natural user-language trigger phrases (e.g. the equivalents of 'help me hold onto this' / 'don't forget') into the description so the 'when' clause reads as something a user would actually say.

Consider naming the concrete recognition action (classify the source's intent into one of the four dispositions) before listing outputs, so the 'what' reads as an action rather than only a result set.

DimensionReasoningScore

Specificity

Names the domain and lists four concrete dispositions ("abstain, admit, offer, or retry") plus explicit exclusions; not a comprehensive set of concrete operations, so it sits at 4 rather than 5.

4 / 5

Completeness

Both halves are explicit ("Use when a source may entrust work" for when; "Output: abstain, admit, offer, or retry" for what), but the 'when' is a condition rather than concrete trigger phrases, keeping it below 5.

4 / 5

Trigger Term Quality

The description enumerates scenario categories ("casual mentions", "terminal offers", "generic planning", "Schedule/Needs Me") but omits the natural user-language phrases, which live in the separate triggers field rather than the description itself.

3 / 5

Distinctiveness Conflict Risk

A clear niche (source-entrusted custody recognition) with explicit exclusions that directly neutralize the main overlap risks (generic planning, Schedule/Needs Me), giving minimal conflict risk.

5 / 5

Total

16

/

20

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
zts212653/clowder-ai
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.