CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

speckit-converge

Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.

Quality

70%

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 ./.claude/skills/speckit-converge/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 strongly engineered workflow: exact commands, output templates, severity taxonomy, validation checkpoints, and safe outcome branching make it highly actionable and clear. Its main weaknesses are token efficiency (duplicated hook blocks and generic shell advice) and organization (the hook spec should be factored into a one-level-deep reference file).

Suggestions

Deduplicate the before_converge and after_converge hook blocks into a single shared section (or a references/hooks.md file) differing only in the hook key and template labels, cutting ~40 lines.

Make Step 3's code-scope derivation concrete with an example search command or pattern (e.g. grep for requirement keywords in named source directories).

Remove the generic shell-quoting tip about escaping single quotes, which restates knowledge Claude already has.

DimensionReasoningScore

Conciseness

The core procedural content is efficient, but the ~40-line extension-hook machinery is duplicated nearly verbatim in Pre-Execution Checks and Step 9, and generic shell-quoting advice ("For single quotes in args like \"I'm Groot\"...") explains knowledge Claude already has. Mostly efficient with some clear tightening opportunities, matching anchor 3 rather than 2 because the workflow content itself is non-redundant.

3 / 5

Actionability

The body gives an exact prerequisite command, copy-paste-ready hook output blocks, a precise task-line format ("- [ ] T042 <imperative description> per <source-ref> (<gap-type>)"), and a concrete example findings row. It falls short of anchor 5 only because Step 3's "keyword search for the concepts each requirement describes" provides no concrete command or example query.

4 / 5

Workflow Clarity

Nine explicitly sequenced steps with STOP conditions for missing artifacts, a pre-write validation checkpoint (findings summary before any file write), two clearly branched outcomes (converged / tasks_appended), append-only and byte-for-byte-unchanged guards, and explicit error handling for unparseable extensions.yml. This matches anchor 5: clear sequence, explicit validation, and error-recovery feedback loops.

5 / 5

Progressive Disclosure

The file is well-sectioned with clear headers and numbered steps, but roughly 80 of ~270 lines are duplicated before/after hook boilerplate that clearly belongs in a single shared reference file, matching anchor 3 ("content that should be separate is inline"). Not anchor 4 because the duplication is a substantial organization gap, not a minor one; not anchor 2 because navigation and structure are otherwise clear.

3 / 5

Total

15

/

20

Passed

Description

58%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 communicates a clear, concrete what with a distinct spec-kit identity, but it lacks any "when to use" trigger guidance and has thin natural-keyword coverage. Adding an explicit use-when clause with user-facing trigger phrases would materially improve it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the implementation appears incomplete relative to the feature's spec, or after /speckit-implement when unbuilt requirements are suspected."

Include natural trigger terms users would actually say, such as "converge", "gap analysis", "remaining work", "spec compliance", or "check what's left to build".

Briefly mention the outcome taxonomy (converged vs. tasks appended) so the skill's result is distinguishable from /speckit-implement and /speckit-tasks at trigger time.

DimensionReasoningScore

Specificity

Two concrete actions are named with specific artifacts — "Assess the current codebase against the feature's spec, plan, and tasks" and "append any remaining unbuilt work as new tasks to tasks.md" — giving clear, executable capability statements. It stops short of anchor 5 because only two actions are listed and behaviors like gap classification or severity grading are not mentioned.

4 / 5

Completeness

The "what" is clearly answered (assess codebase against spec/plan/tasks, append remaining work to tasks.md), but there is no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guideline. It is not a 4 because the "when" is entirely absent rather than merely implicit or underspecified.

3 / 5

Trigger Term Quality

Terms like "spec", "plan", "tasks", "tasks.md", and "unbuilt work" are relevant to the domain but the description misses natural variations and synonyms a user would say, such as "converge", "gap analysis", "remaining work", or "spec compliance". Keyword coverage is partial rather than good, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

The description occupies a distinct spec-kit niche with named artifacts (spec, plan, tasks.md) and a unique append-only action, so it is mostly distinguishable. Minor overlap risk remains with closely related sibling skills like /speckit-implement and /speckit-tasks, which keeps it below anchor 5.

4 / 5

Total

14

/

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

RihardsJ/software-factory

Path

.claude/skills/speckit-converge/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.