CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-promote

Draft launch or promotion copy for a shipped feature.

59

Quality

69%

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 ./skills/ce-promote/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.

The body is a tight, well-structured decision tree: a clear four-phase workflow with explicit branch conditions, validation checkpoints, and error-recovery fallbacks at every fragile point, plus one purposeful one-level-deep reference. Its only real weaknesses are minor: a few rationale-heavy sentences that could be trimmed and slightly incomplete inline command detail for the Spiral path.

Suggestions

Trim the explanatory asides that restate the reference's content inline (the "naive config scan misreads ce-setup's commented template" sentence and the duplicated Spiral-optionality framing) to save tokens.

Inline the single `spiral write` invocation skeleton (flags only, e.g. `--instant --json`) in Path A so the happy path is executable without opening the reference.

DimensionReasoningScore

Conciseness

The body is dense with instructions and assumes Claude's competence (no explanation of what git or a changelog is), but a few rationale-heavy passages could be trimmed — e.g. the "a naive config scan misreads ce-setup's commented template example" aside and the double explanation of Spiral optionality in the intro and Path B. Anchor 4 (efficient, minor over-explanation) rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Guidance is mostly executable: copy-paste commands (`gh pr view --json title,body,url`, `git diff main...HEAD --stat`, `which spiral`, `spiral auth status --json 2>/dev/null`), a concrete output template, and per-channel shape specs. Minor gaps remain — the actual `spiral write` invocation and its flag semantics are delegated to the reference, and the Phase 1 fallback ordering of sources is left to judgment. Anchor 4 rather than anchor 5's fully copy-paste-ready common cases.

4 / 5

Workflow Clarity

The four phases are explicitly sequenced with a validation checkpoint at the fragile point: the Spiral state detection (Ready/Absent/Unauthed) gates which path runs, Phase 1 has an ask-don't-guess checkpoint ("ask one short question rather than guessing"), and every failure mode has an explicit recovery fallback ("fall back silently to Path B", "never let a Spiral failure... block the skill", Path 0 decline always proceeds). This matches anchor 5's explicit validation steps with error-recovery feedback loops.

5 / 5

Progressive Disclosure

The body is a well-organized decision tree (~80 lines) that keeps the detailed CLI mechanics in one clearly-signaled, one-level-deep reference: `references/spiral-cli.md` is cited twice with explicit purpose ("Read ... before composing the prompt"; "read ... and follow its Path 0 section"), and that file exists with the cited Path 0 section and the cue-word/`--num-drafts` gotcha the body defers to. Anchor 5: clear overview, well-signaled references, easy navigation.

5 / 5

Total

18

/

20

Passed

Description

53%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 concise, third-person, and states a clear single capability, but it is under-specified for discovery: no "when to use" trigger clause, no channel/output enumeration, and thin keyword coverage. It reads as a correct but minimal one-line summary rather than a discovery surface.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to announce, promote, or write launch/release copy for a feature that just shipped."

Enumerate the concrete output types (X post or thread, changelog/release blurb, LinkedIn, email, blog intro, demo script) so the "what" is comprehensive and channel-specific queries match.

Include natural synonyms users would say ("announcement", "release notes", "tweet", "marketing copy") to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

"Draft launch or promotion copy for a shipped feature" names the domain and one concrete action (drafting copy), but lists no other capabilities or output types (channels, changelog blurbs, threads). It matches anchor 3 — more than the minimal/generic anchor 2, but not the several-specific-actions coverage of anchor 4.

3 / 5

Completeness

The description has a clear "what" (draft launch or promotion copy for a shipped feature) but no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not anchor 4, which requires both what and when present.

3 / 5

Trigger Term Quality

"launch", "promotion copy", and "shipped feature" are relevant keywords, but common natural variations users would say — "announce", "release notes", "tweet", "marketing copy" — are absent. Anchor 3 (some relevant keywords, missing synonyms) fits better than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"Promotion copy for a shipped feature" carves a fairly distinct niche with clear ties to launch/release context, with only minor overlap risk against general writing or changelog skills. Not anchor 5, since the trigger surface is narrow and lacks distinctive explicit triggers.

4 / 5

Total

13

/

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
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.