CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-pov

Give a decisive, project-grounded point of view: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a supplied approach set. Use for a solo POV. Use when asked to consult other models, reconcile their opinions, or `oracle`. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

68

Quality

83%

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

78%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 a well-structured, progressive-disclosure skill: phased workflow with explicit checkpoints and clean delegation to one-level references. It assumes competence and avoids padding, with only minor repetition in the Artifact Root section and validation detail mostly living in referenced files.

Suggestions

De-duplicate the resolve-`<root>` directive between the "## Artifact Root" intro and the fenced `ce-docs-root` block to tighten conciseness.

Inline a brief error-recovery loop (failed floor -> what the failure result is per shape -> next step) so workflow_clarity's validation feedback loop is visible in SKILL.md rather than only in references/method.md.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence with no padding or basic-concept explanation, but the "## Artifact Root" intro line and the fenced `ce-docs-root` block restate the same resolve-`<root>` directive, a minor instance of repetition that could be trimmed.

4 / 5

Actionability

Guidance is concrete and directive ("Read `references/intake.md` now", "Send scouts directly to candidate-specific current evidence") with real commands like `git rev-parse --show-toplevel`, but as an instruction-only skill some steps resolve into referenced files rather than fully inline executable detail.

4 / 5

Workflow Clarity

A clear Phase 0–4 sequence with explicit per-phase "read this reference now" checkpoints and the grounding/floor gate providing validation, though error-recovery feedback loops are mostly delegated to the referenced files rather than stated inline.

4 / 5

Progressive Disclosure

A concise overview body signals one-level-deep references to real files (method.md, intake.md, grounding.md, cross-model-panel.md, followup.md, boundaries.md), each introduced at its point of use, with no nested reference chains.

5 / 5

Total

17

/

20

Passed

Description

87%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 is strong: it states a concrete purpose, gives explicit trigger guidance, and disambiguates from sibling skills with clear "not for" boundaries. Minor specificity gains are available by enumerating the three POV shapes more concretely.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions — "a graded verdict on an external-adoption question", "a holistic take on a document", "or a position on a supplied approach set" — but these shapes stay somewhat abstract rather than fully enumerated, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ("Give a decisive, project-grounded point of view" in three named shapes) and when ("Use for a solo POV. Use when asked to consult other models, reconcile their opinions, or `oracle`") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say ("consult other models", "reconcile their opinions", "oracle", "solo POV"), though a few common synonyms for the consulting/reconciliation intent are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche reinforced by explicit exclusion clauses naming sibling skills ("Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm)"), minimizing conflict risk.

5 / 5

Total

18

/

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
EveryInc/compound-engineering-plugin
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.