CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

flow-deliver

Multi-AI validation, scoring, and review using available external providers (Double Diamond Deliver phase)

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/flow-deliver/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%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 content is highly actionable with a rigorous enforced execution contract, but it is severely bloated by duplication — the same banners, context-detection rules, and step sequences appear multiple times with inconsistent numbering. Consolidating to a single authoritative step sequence and moving the example report to a reference file would cut the token cost roughly in half without losing guidance.

Suggestions

Delete the duplicated sections: the second 'MANDATORY: Context Detection & Visual Indicators' block, the repeated banner templates in 'Visual Indicators', and the 'How It Works' step list — keep only the EXECUTION CONTRACT as the single authoritative sequence.

Move the 100+ line Example 1 validation report to a references/example-report.md file and keep a one-line pointer plus a short skeleton of the report format inline.

Reconcile the three numbering schemes (7-step contract, 5-step How It Works, 5-step Implementation Instructions) into one numbered sequence so the model cannot follow a stale or conflicting variant.

DimensionReasoningScore

Conciseness

The ~900-line body is heavily padded through verbatim duplication: the provider banner template appears four times, context-detection instructions appear twice (EXECUTION CONTRACT Step 1 and the later 'MANDATORY: Context Detection' section), and the workflow steps are restated under three competing numbering schemes (7-step contract, 5-step 'How It Works', 5-step 'Implementation Instructions'). This matches 'Severely verbose... heavily padded' rather than 2, where padding would be limited to a few sections.

1 / 5

Actionability

The skill provides concrete, mostly copy-paste-ready bash: the exact orchestrate.sh invocation with run-marker validation, the check-providers.sh call, the PR-posting block, and per-step error-handling directives. It falls short of 5 due to placeholder gaps like `TaskUpdate({taskId: "..."})` and template banners with unfilled bracket slots.

4 / 5

Workflow Clarity

The 7-step EXECUTION CONTRACT is clearly sequenced with blocking gates ('DO NOT PROCEED TO STEP N until...'), an explicit validation step (Step 5 verifies the report file), and per-step error handling with feedback ('If validation fails: report, show logs, do not proceed'). It does not reach 5 because the duplicated restatements of the workflow in 'How It Works' and 'Implementation Instructions' use different step numbering, creating drift risk about which sequence governs.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), and the body inlines large content that belongs in separate files — a 100+ line example validation report and repeated banner templates. Section headers do provide navigable structure and external skill/script references are named, matching 'Some structure but could be better organized... content that should be separate is inline' rather than 2's 'minimal structure'.

3 / 5

Total

12

/

20

Passed

Description

50%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 'what' with a distinct multi-provider angle, but it entirely lacks a 'when to use' clause and natural trigger coverage is thin. It reads as a domain label rather than an activation guide.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when the user asks to review, validate, test, or quality-check code or documents before shipping').

Include natural keyword variations users would say — 'test', 'check', 'quality check', 'audit', 'verify' — alongside 'validation', 'scoring', and 'review'.

Make the capabilities slightly more concrete, e.g., 'Runs Codex and Antigravity reviews, synthesizes a scored validation report with quality gates' instead of generic 'validation, scoring, and review'.

DimensionReasoningScore

Specificity

The description names its domain ('Multi-AI validation, scoring, and review') and lists a few actions, but the actions remain generic labels rather than concrete capabilities, matching 'Names domain and 1-2 concrete actions, but not comprehensive'. It does not reach 4 because there is no specifics about what the validation, scoring, or review actually cover.

3 / 5

Completeness

The 'what' is clear (multi-AI validation/scoring/review via external providers) but there is no 'Use when...' clause; the '(Double Diamond Deliver phase)' parenthetical only weakly implies timing. Per the judging guidelines, a missing explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

'validation', 'scoring', and 'review' are natural user phrases, but common variations users would actually say — 'test', 'check', 'quality check', 'audit', 'verify' — are missing, matching 'Some relevant keywords but missing common variations or synonyms'. It is above 2 because the included terms are genuinely natural, not pure jargon.

3 / 5

Distinctiveness Conflict Risk

'Multi-AI' and 'Double Diamond Deliver phase' provide some distinctiveness, but 'validation, scoring, and review' is broad territory that overlaps with generic code-review and quality-check skills, matching 'Somewhat specific but could still overlap with similar skills'. It is not 4 because the trigger surface ('review X', 'validate Y') collides with many common review skills.

3 / 5

Total

12

/

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 (939 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-deliver/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.