CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-compound-refresh

Old name for refreshing learnings, which now lives in `ce-compound`. Use only when a prompt or standing instruction names `ce-compound-refresh`; use `ce-compound` for every other learnings audit.

Quality

92%

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.

An exemplary deprecation-shim body: fully executable instructions with exact strings, a clearly ordered three-step workflow with conditional handling, and lean prose where every clause justifies a rule. Nothing is missing for its purpose and nothing could be cut without losing correctness.

DimensionReasoningScore

Conciseness

At ~24 lines, every sentence carries a functional rule or a rationale that prevents a predictable mistake (e.g., "because nobody is present and the plain word would run a capture", "A refresh report is long, and a scheduled run may show only its final message"). No padding, no explanation of concepts Claude already knows — anchor 5. It stays above anchor 4 because the few explanatory clauses earn their place by justifying non-obvious rules rather than being trimmable over-explanation.

5 / 5

Actionability

The guidance is copy-paste ready: the exact notice text to print verbatim, the exact delegation command ("Invoke the `ce-compound` skill with `mode:refresh` followed by every argument you received, unchanged"), and the exact alternative notice for non-interactive mode. As an instruction-only skill the absence of code is not penalized, and the specific strings cover the common cases (default, mode:non-interactive/headless, host-specific rendering) — anchor 5.

5 / 5

Workflow Clarity

"Do these in order:" introduces an explicit, unambiguous three-step sequence (print notice → delegate with mode:refresh → print notice again as the last line), including a conditional branch for non-interactive runs and a guard explaining why mode:refresh must be present. This is a simple, non-destructive skill where the single action is unambiguous, so per the simple-skill note it merits 5; anchor 4 would require missing checkpoints, and there are none needed here.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent) and no content that warrants external files; the body is well organized with a title, a Done criterion, a host-rendering rule, and a numbered procedure. Per the rubric's guideline for short skills needing no external references, this merits 5.

5 / 5

Total

20

/

20

Passed

Description

82%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 well-crafted deprecation-alias description: it states exactly what the skill is, gives a precise exclusive trigger, and actively routes every other case to the successor skill, which eliminates conflict risk. Its only weakness is that it names just one concrete capability, which is inherent to being a redirect stub.

DimensionReasoningScore

Specificity

"Old name for refreshing learnings, which now lives in `ce-compound`" names the domain and a single concrete action (refreshing learnings), but lists no further specific capabilities. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) — above anchor 2 because "refreshing learnings" is specific rather than generic, below anchor 4 because there are not several distinct actions.

3 / 5

Completeness

It explicitly answers both questions: what ("Old name for refreshing learnings, which now lives in `ce-compound`") and when ("Use only when a prompt or standing instruction names `ce-compound-refresh`; use `ce-compound` for every other learnings audit") with a concrete trigger phrase. This matches anchor 5; anchor 4 would require the 'when' to be less explicit than the fully concrete trigger given here.

5 / 5

Trigger Term Quality

Natural terms present: "refreshing learnings", "learnings audit", and the exact deprecated name "ce-compound-refresh", giving good keyword coverage of the niche. It sits at anchor 4 rather than 5 because common synonyms (e.g., "update learnings", other phrasings of the audit) are not covered, and above anchor 3 because multiple relevant natural phrases appear, not just one.

4 / 5

Distinctiveness Conflict Risk

The trigger is an exact name match ("Use only when a prompt or standing instruction names `ce-compound-refresh`") and it explicitly disambiguates against its only sibling ("use `ce-compound` for every other learnings audit"), giving a clear niche with minimal conflict risk — anchor 5. Anchor 4 would require some residual overlap risk, which the explicit routing rule eliminates.

5 / 5

Total

17

/

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.

Validation — 15 / 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

EveryInc/compound-engineering-plugin

Path

skills/ce-compound-refresh/SKILL.md

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.