CtrlK
BlogDocsLog inGet started
Tessl Logo

context-self-management

Use when: context_management_hint 或长 session repo/projectPath 混淆。Not for: 普通 context 焦虑/跨猫交接。Output: handoff/续/冲刺判断。

67

Quality

81%

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

100%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.

The body is an exemplary concise decision skill: a tight self-check checklist with objective anchors, a 2x2 decision matrix covering all branches, concrete per-branch actions naming the exact tool and its required contents, and an explicit anti-pattern section. Nothing is padded, and every decision path is executable from what is written.

DimensionReasoningScore

Conciseness

The ~28-line body is pure decision content — signal interpretation, anchors, a 2x2 matrix, and per-cell actions — with no padding and no explanation of concepts Claude already knows. Every line earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

The guidance is fully executable: it interprets every fillConfidence enum value (exact_token / approx_token / bytes_health / unavailable), gives an objective anchor (compressionCount > 0), names the exact tool cat_cafe_propose_session_handoff, and enumerates the five handoff items. As an instruction-only skill with concrete, complete guidance, the absence of code is not penalized, and all common decision branches are covered.

5 / 5

Workflow Clarity

A clear sequence (hint -> three-question self-check -> 2x2 matrix -> per-cell action) with an explicit checklist of checkpoints, per-value signal interpretation, and a human gate on the one risky operation ('提案要人来 gate,你不自己封'). The anti-pattern section adds error-recovery guidance; the destructive-operation cap does not apply because the handoff is explicitly human-gated.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references (verified: no references/, scripts/, or assets/ directories exist), and the body is organized into clear ## sections (self-check, decision matrix, actions). Per the simple-skill exception, this earns full marks.

5 / 5

Total

20

/

20

Passed

Description

62%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.

The description uses a clear Use when / Not for / Output scaffold that answers both what and when and explicitly excludes neighboring skills, but it is compressed to the point of crypticness. Heavy reliance on internal jargon and mixed-language shorthand limits how naturally it communicates capabilities and triggers.

Suggestions

Expand the 'Output' clause into 2-3 concrete capability statements (e.g., 'Runs a three-question self-check on session state, applies a 2x2 handoff/sprint/continue decision matrix, and drafts the five-item handoff') to raise specificity.

Add natural-language trigger phrasings alongside the system signal (e.g., 'context feels drifted', 'session been compressed multiple times', 'losing track of which repo') so trigger quality doesn't depend solely on the jargon term 'context_management_hint'.

Spell out what the three-way judgment (handoff/续/冲刺) means in plain terms, since the current shorthand assumes familiarity with the skill's internal vocabulary.

DimensionReasoningScore

Specificity

'Output: handoff/续/冲刺判断' names the domain and one concrete output (a three-way judgment), but the description never enumerates the actual actions (self-check, decision matrix, handoff tool call), matching the '1-2 concrete actions, not comprehensive' anchor. It is not a 4 because no list of several specific capabilities appears.

3 / 5

Completeness

Explicit 'Use when:' and 'Output:' clauses answer both when and what, and a 'Not for:' clause adds scope — both present but 'when' is terse and jargon-dependent. Not a 5: the trigger guidance lacks concrete, naturally-phrased trigger conditions.

4 / 5

Trigger Term Quality

Triggers mix a few natural phrases ('话题漂移', '要不要 handoff') with heavy internal jargon ('context_management_hint', 'repo/projectPath 混淆'), giving some relevant keywords but missing common variations a user would say. Not a 4: coverage is narrow and the primary trigger is a system signal rather than natural user language.

3 / 5

Distinctiveness Conflict Risk

'Not for: 普通 context 焦虑/跨猫交接' explicitly fences off adjacent skills and the triggers are narrow, making it mostly distinct with minor overlap risk. Not a 5: it still conceptually overlaps general context-compression/continuation guidance.

4 / 5

Total

14

/

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.