CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

update

Use when the user asks to reconcile the project's AGENTS.md, CLAUDE.md and scaffolded files with the current flowai templates after a framework upgrade. Not for first-time setup, and not for tailoring the installed skills.

72

Quality

90%

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

92%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 operationally excellent body: concrete commands, verbatim messages, exhaustive path precedence, and validation checkpoints (diff-before-write, per-file confirmation, verify step, checklist) covering all batch-write risks. Its only weakness is mild redundancy — the scoping negations are repeated between the Overview, Rules, and steps.

DimensionReasoningScore

Conciseness

Almost all content is project-specific operational detail (install tiers, path precedence, template priority) that Claude cannot already know, but the "no CLI lifecycle / no primitive adaptation" negation is stated in both Overview and Rules, and the read-only-source constraint is repeated across context, rule 3, and step 8 — minor duplication that could be trimmed.

4 / 5

Actionability

Fully executable guidance throughout: exact flag parsing, exhaustive path lists in precedence order, a copy-paste-ready invocation of the bundled compare_rules.py with its exit-code contract, verbatim stop messages, an exact verification git diff command, and a concrete per-file proposal format with a worked example (the TDD CHECK step rationale).

5 / 5

Workflow Clarity

Nine clearly sequenced steps with validation checkpoints at every risky point: diff-before-write (rule 5), per-file confirmation before each write (steps 7–8), a script exit-2 fix-and-rerun feedback loop (step 4), a verify step with the exact git diff, and a final verification checklist — well above the batch/destructive-operation cap.

5 / 5

Progressive Disclosure

Scored against the actual bundle: the 37KB AGENTS.template.md is kept in assets/ and referenced via its installed skill-local paths, compare_rules.py lives in scripts/ and is signaled with its exact invocation and behavior (read-only, exit codes), and the body is procedure only — one level deep with clearly tagged sections and easy navigation.

5 / 5

Total

19

/

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.

A strong description: an explicit "Use when" trigger tied to a concrete event (framework upgrade), concrete artifact names, and clear negative scoping that separates it from sibling commands. The only gap is vocabulary breadth — it relies on the single verb "reconcile" where users might say "update" or "sync".

DimensionReasoningScore

Specificity

"reconcile the project's AGENTS.md, CLAUDE.md and scaffolded files with the current flowai templates after a framework upgrade" names one action applied to three concrete artifact classes plus a concrete condition — specific, but the sub-actions (rule-level diffing, symlinking CLAUDE.md) are not enumerated as in the anchor-5 example.

4 / 5

Completeness

It clearly states what ("reconcile the project's AGENTS.md, CLAUDE.md and scaffolded files with the current flowai templates") and an explicit, concrete when ("Use when the user asks to reconcile ... after a framework upgrade"), with negative scoping on top; the 'when' is explicit rather than weakly implied, matching the anchor-5 example.

5 / 5

Trigger Term Quality

"framework upgrade", "flowai templates", "AGENTS.md", "CLAUDE.md", "scaffolded files" and the explicit "Use when the user asks to reconcile" give good keyword coverage, but natural synonyms users would say — "update", "sync", "refresh", "flowai upgrade" — are absent since only "reconcile" is used.

4 / 5

Distinctiveness Conflict Risk

"Not for first-time setup, and not for tailoring the installed skills" explicitly fences off the adjacent init/adapt commands, and flowai-specific artifact names give this a clear niche with minimal overlap risk against other skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

14

/

16

Passed

Repository

korchasa/flowai-plugins

Path

plugins/flowai/skills/update/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.