CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flow-define

Multi-AI requirements scoping using available external providers (Double Diamond Define phase). Priority triggers: octo define, octo scope, co-define, co-scope. DO NOT use for implementation, research, review/validation, or built-in commands.

Quality

71%

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/flow-define/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 exceptionally actionable and the enforced seven-step workflow is clearly sequenced with robust validation and error recovery. Its weaknesses are severe redundancy (the workflow, banner, and provider roles are each described multiple times) and a monolithic structure with no reference files to absorb examples and templates.

Suggestions

Collapse the duplicated sections: keep the Execution Contract as the single authoritative procedure and delete or heavily trim the "How It Works" Stages A-D and "Implementation Instructions" restatements, which repeat the same seven steps.

Move the ~100-line Example 1 and the full Problem Definition format template into a separate references/ file (e.g., references/examples.md) and reference it one level deep from the body.

Remove the duplicate banner specification in the "Visual Indicators" section by pointing back to the STEP 1 banner requirement (the comment already notes it lives there).

DimensionReasoningScore

Conciseness

The ~790-line body is noticeably padded with duplication: the same seven-step workflow is restated three times (Execution Contract, "How It Works" Stages A-D, and "Implementation Instructions"), the provider banner is specified twice (STEP 1 and the "Visual Indicators" section), and Example 1 is a ~100-line fully worked sample, so well over a third of the tokens are redundant.

2 / 5

Actionability

Guidance is fully executable: exact bash with plugin-root fallback chains, signal traps, and exit-status handling; a complete provider-check script; full AskUserQuestion option specifications; a precise orchestrate.sh invocation with validation and a recovery command; and a copy-paste output format template covering the common case.

5 / 5

Workflow Clarity

Seven mandatory, explicitly blocking steps are sequenced with validation checkpoints at each boundary ("DO NOT PROCEED TO STEP N until..."), Step 5 verifies the synthesis report, error handling is specified per step, and failure paths include feedback loops (show logs, offer restore/discard, never fall back to direct analysis), matching the checklist-plus-recovery anchor.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so everything lives in one ~800-line file; the plugin-block references at the top are clearly signaled, but the worked examples and the full Problem Definition format template are inline content that clearly belongs in separate reference files, fitting the "some structure but could be better organized" anchor.

3 / 5

Total

15

/

20

Passed

Description

62%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 niche with explicit trigger guidance and explicit exclusions, which is above average. Its main weaknesses are command-style trigger terms instead of natural user phrasing and a single-action capability statement rather than a fuller enumeration of what the skill does.

Suggestions

Replace or augment the command-style triggers with natural phrases users would say, e.g. "Use when the user says 'define the requirements for X', 'clarify the scope of Y', or 'what exactly does X need to do'".

Enumerate the concrete capabilities the skill provides (e.g., "define core requirements, identify technical constraints, surface edge cases, set scope boundaries") instead of the single phrase "requirements scoping".

Add a boundary clarifying that generic coding uses of "define" (e.g., defining a variable or function) do not invoke this skill.

DimensionReasoningScore

Specificity

"Multi-AI requirements scoping using available external providers" names the domain and one concrete action (scoping requirements), but does not enumerate the several specific actions the skill performs (define requirements, clarify scope, identify constraints, edge-case analysis), matching the 1-2-concrete-actions anchor rather than the comprehensive one.

3 / 5

Completeness

Both what ("Multi-AI requirements scoping using available external providers") and when ("Priority triggers: octo define, octo scope, co-define, co-scope") are present, plus explicit negative guidance ("DO NOT use for implementation, research, review/validation, or built-in commands"); the when-clause relies on command names rather than concrete natural trigger phrases, so it is not a 5.

4 / 5

Trigger Term Quality

"Priority triggers: octo define, octo scope, co-define, co-scope" are command-style invocations rather than natural user phrases; relevant keywords (define, scope) are present but common variations users would actually say ("define the requirements for X", "clarify the scope of Y") are missing from the description itself.

3 / 5

Distinctiveness Conflict Risk

The Double Diamond Define-phase niche and the explicit "DO NOT use for implementation, research, review/validation" boundary keep it mostly distinct from sibling workflows, but the generic words "define" and "scope" could still match non-requirements requests (e.g., "define this constant"), leaving minor overlap risk.

4 / 5

Total

14

/

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

skill_md_line_count

SKILL.md is long (828 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

nyldn/claude-octopus

Path

.claude/skills/flow-define/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.