CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sy-reframe

Plan a stuck, stale, or unsafe frame into a smaller viable direction with rollback and decision boundaries. Use when a migration, plan, PR, or implementation path is producing churn, conflicting claims, or unsafe scope.

Quality

79%

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-reframe/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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, token-efficient stage contract: a sequenced procedure with an explicit fail-fast validation gate, concrete status vocabulary, error-recovery routing, and a clean one-level-deep reference bundle that keeps detail out of the overview. The residual gap is mild underspecification of the validation commands and no in-context pointers to when each reference file should be read.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — sections like "Record evidence refs and classify each lane as pass, fail, blocked, or not_checked" and "stop at the first failed required gate, classify the blocker, and do not proceed" carry operational content with zero padding or explanation of concepts Claude already knows. Every section earns its tokens, matching anchor 5.

5 / 5

Actionability

For an instruction-only orchestration skill the guidance is mostly executable: a five-step procedure, explicit status vocabulary (pass/fail/blocked/not_checked), named handoff targets (brainstorm, reconcile, reinforce), and concrete deliverable fields (schema_version, evidence_refs, blocked_by, next_stage). It falls short of anchor 5 because instructions like "Run the smallest relevant local check for changed files" and "run plugin validation and SDK proof commands from the repository wrapper" stop short of naming the actual commands.

4 / 5

Workflow Clarity

The Procedure is a clear five-step sequence with an explicit fail-fast validation checkpoint ("stop at the first failed required gate, classify the blocker, and do not proceed to downstream stages") and error-recovery routing in Failure modes, matching anchor 4. It does not reach anchor 5 because the validation step is stated as policy rather than an executable check with a fix-and-retry loop tied to a specific command.

4 / 5

Progressive Disclosure

The body is a concise overview with a dedicated References section pointing one level deep to four clearly labeled files (contract, evals, task profile, source context), all of which exist in ./references/, and detailed contract material is appropriately split out rather than inlined. It misses anchor 5 only because the references are listed at the end without guidance on when in the workflow each file should be consulted.

4 / 5

Total

17

/

20

Passed

Description

66%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 follows the strong what-plus-when pattern with a genuine trigger phrase, and the when-clause contains realistic keywords. Its weakness is abstraction: the 'what' leans on internal jargon ('frame', 'decision boundaries') rather than concrete, plain actions, and the broad trigger surface creates overlap risk with general planning and review skills.

Suggestions

Rewrite the 'what' clause with concrete plain-language actions, e.g. 'Restructure a stuck or unsafe plan into a smaller viable scope, define rollback points, and set decision boundaries for proceeding or stopping' — this would lift specificity from 3 toward 4-5.

Add natural user phrasings to the trigger clause (e.g. 'the plan is stuck or spinning', 'we keep churning on this migration', 'scope feels unsafe') to improve trigger term coverage toward anchor 5.

Narrow the trigger surface to reduce conflict with generic planning/review skills — e.g. specify that this applies when a SynAIpse lifecycle stage needs reframing, rather than any 'plan or PR producing churn'.

DimensionReasoningScore

Specificity

The description names the domain and a concrete action ("Plan a stuck, stale, or unsafe frame into a smaller viable direction with rollback and decision boundaries"), but the vocabulary is abstract jargon ('frame', 'decision boundaries') and only one real action (planning/reframing) is stated. It sits at anchor 3 — domain plus 1-2 concrete actions, not comprehensive — rather than 4, which would require several specific listed actions.

3 / 5

Completeness

Both what ("Plan a stuck, stale, or unsafe frame into a smaller viable direction with rollback and decision boundaries") and when ("Use when a migration, plan, PR, or implementation path is producing churn, conflicting claims, or unsafe scope") are explicitly present with a concrete trigger phrase. It does not reach anchor 5 because the 'what' relies on unexplained abstract terms, so the pair is explicit but not maximally concrete.

4 / 5

Trigger Term Quality

The when-clause includes natural terms a user would plausibly say: "migration, plan, PR, or implementation path is producing churn, conflicting claims, or unsafe scope". Coverage is good, matching anchor 4, but common variations users might actually say ('stuck', 'spinning', 'scope creep', 'pivoting the approach') are missing, so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The description is somewhat specific to an orchestration/reframing niche, but the trigger surface — "migration, plan, PR, or implementation path" producing churn — overlaps broadly with generic planning, code-review, and migration skills, matching anchor 3. It is more distinctive than anchor 2's near-generic breadth but lacks the tight, unambiguous triggers of anchor 5.

3 / 5

Total

14

/

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-reframe/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.