CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sy-execution-plan

Plan how to implement one approved slice, including file targets, validation gates, rollback, and proof lanes. Use when a slice spec is accepted and the user needs the implementation order before code changes.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./Plugins/synaipse-harness/skills/sy-execution-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 skill body is a compact, well-structured orchestration protocol: clear when-to-use, sequenced procedure with an explicit fail-fast gate, and a clean one-level-deep reference bundle. Its main weakness is actionability — the circular 'work owned by execution-plan' phrasing and the absence of any concrete stage-result template or example leave the executor dependent on the reference files to know exactly what to produce.

Suggestions

Include a minimal inline example of the stage-result artifact (a few lines showing schema_version, stage, status, evidence_refs, blocked_by, next_stage) so the deliverable is executable without opening contract.yaml.

Replace the circular 'Perform only the work owned by execution-plan' with the concrete scope (e.g., 'Decide implementation order, name target files, select validation gates, and define rollback steps — not writing the code').

Add a load-when hint to each References entry (e.g., 'contract: required for artifact fields; source-context: only when provenance is needed') and drop the verbatim duplicate of the description in When to use.

DimensionReasoningScore

Conciseness

The body is lean with no over-explanation of known concepts, but the When-to-use section duplicates the frontmatter description verbatim and Failure modes overlaps Gotchas (e.g., 'Missing previous-stage artifact: block and request...' vs. procedure step 2). Anchor 4 fits: efficient with minor trimming possible; not 5 because of the duplication and redundancy.

4 / 5

Actionability

Concrete elements exist (Deliverables enumerates 'schema_version, stage, status, evidence_refs, blocked_by, and next_stage' and the pass/fail/blocked/not_checked vocabulary), but steps like 'Perform only the work owned by execution-plan' are circular and the body never shows an artifact template or example — key execution details are missing. Anchor 3 rather than 4 because the guidance is not mostly executable standing alone.

3 / 5

Workflow Clarity

A clear 5-step Procedure with an explicit fail-fast checkpoint ('stop at the first failed required gate... do not proceed to downstream stages') and exit-criteria gating of the handoff; the operation is a planning stage, so the destructive/batch cap does not apply. Not 5 because actual gate commands are unspecified ('run plugin validation and SDK proof commands from the repository wrapper') and no validate→fix→revalidate loop is stated.

4 / 5

Progressive Disclosure

The body is a well-organized overview whose References section links all four real bundle files (contract.yaml, evals.yaml, task-profile.json, source-context.yaml) one level deep with short labels. Anchor 4 rather than 5 because the body gives no load-when guidance per reference (that lives inside source-context.yaml) and labels are terse.

4 / 5

Total

15

/

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.

The description cleanly answers both what and when with a well-scoped lifecycle trigger, and its 'Use when' clause is explicit and concrete. Weaknesses are the single action verb padded with plan components, and heavy internal jargon ('slice spec', 'proof lanes') that limits natural trigger-term coverage and keeps slight conflict risk within the sibling stage-skill family.

Suggestions

Convert plan components into distinct actions or name the deliverable more operationally (e.g., 'Produce an execution plan that names target files, picks validation gates, and defines rollback steps') to lift specificity.

Add user-natural trigger synonyms alongside the harness terms, e.g., 'Use when a slice or task spec is approved and the implementation sequence, file list, or rollback plan is needed before coding starts.'

Differentiate from siblings by naming the boundary explicitly in the description (e.g., '...before code changes — not the coding stage itself') to reduce overlap with sy-work.

DimensionReasoningScore

Specificity

"Plan how to implement one approved slice" names the domain and the enumerated contents ("file targets, validation gates, rollback, and proof lanes") are concrete, but there is only one action verb with plan components rather than the several distinct actions of anchor 4. Not anchor 2 because the description is domain-specific with real content, not generic.

3 / 5

Completeness

Explicitly answers both: what ("Plan how to implement one approved slice, including file targets, validation gates, rollback, and proof lanes") and when ("Use when a slice spec is accepted and the user needs the implementation order before code changes") with concrete trigger conditions. Not 4 because the when-clause is already explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

"implementation order" and "before code changes" are natural phrases, but "approved slice", "slice spec is accepted", and "proof lanes" are internal Harness jargon a user would not naturally say, and common variations/synonyms are missing. Falls between anchors 2 (jargon-dominated) and 3 (some relevant keywords), closer to 3.

3 / 5

Distinctiveness Conflict Risk

Pins a clear lifecycle niche (spec accepted → implementation order, "before code changes" distinguishes it from the work stage), but sibling sy-* stage skills (sy-reframe, sy-work) share vocabulary and routing patterns, creating minor overlap risk. Not 5 due to that family-level closeness.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

jscraik/Agent-Skills

Path

Plugins/synaipse-harness/skills/sy-execution-plan/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.