CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dia-guide

Guides users through the V-Model workflow: takes stock of the current project state, recommends the next phase skill, audits handoff entries for completeness, and runs the Closing Handoff after a successful security audit. The guide does not perform CRUD work on artifacts; every concrete change lives in the phase skill it dispatches to. TRIGGER when the user asks "where do I start", "what comes next", "I am lost in the workflow", "which phase fits", "wo bin ich gerade", "wo soll ich anfangen", "was kommt jetzt", or explicitly requests the V-Model overview or end-to-end orientation. DO NOT trigger for individual phase work (use the specific phase skill instead: business-analysis, requirements-engineering, architecture, coding, testing, security-audit), generic mentions of "workflow", "process", or "next step" inside an already-running phase skill, or when a phase skill is already active.

Quality

81%

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

56%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 highly actionable and well-sequenced, with concrete commands, templates, and a clear detection table for the guide's core moments. Its weaknesses are length-driven: heavy duplication of read-only disclaimers and inlining of cross-skill conventions that should live in the referenced project-conventions bundle, making an ~870-line monolith for a navigation skill.

Suggestions

Move the sections that bind all phase-skills (User Interaction Protocol, Concurrent-agent coordination, Dialog handoffs, Signal layer) into the referenced /project-conventions or a references/ bundle file, leaving one-line pointers — this would cut several hundred lines and fix the monolith.

State the read-only boundary ('the guide recommends; the user invokes; the guide does not call other skills, auto-fix, tag, or write METRICS') once in the opening section and delete the four repeated restatements throughout.

Replace the garbled two-column ASCII workflow diagram (comments colliding mid-line) with a simple phase table or list, or move the detailed per-phase input/output mapping into a reference file since the entry-point detection table already covers the routing decision.

DimensionReasoningScore

Conciseness

At ~870 lines for a self-described 'read-only orientation layer', the body is noticeably verbose: the non-invocation disclaimer ('the guide does not call other skills / does not auto-fix') is repeated in at least four sections, and whole sections (User Interaction Protocol, Concurrent-agent coordination, Dialog handoffs, Signal layer) restate conventions that bind 'all phase-skills' and belong in the referenced /project-conventions files. It is not a 1 because the content is project-specific workflow knowledge Claude would not already know, not explanations of basic concepts; it is below a 3 because the padded and duplicated sections are several, not incidental.

2 / 5

Actionability

Most operations are concrete and executable: a copy-paste git branch-creation block, exact flow.py invocations (create-issue, tag-phase, status --item <ID>, promote-to-epic --rename-branch), the mkdir/touch initialization commands, the entry-point detection table, and report templates with literal output formats. It falls short of 5 because some steps remain descriptive rather than executable — e.g. 'Update BACKLOG row: Status -> Ready' without the row's binding format, and 'reads git state' with no concrete command; it is above 3 because the gaps are minor against broad command coverage.

4 / 5

Workflow Clarity

Each guide moment is a numbered, clearly sequenced procedure (branch creation, post-RE promotion with a user-driven AskUserQuestion gate before batch writes, handoff-state audit over five named surfaces, three-step entry-point detection, four-step Closing Handoff), with the feature-complete audit providing explicit verification ('Verdict: feature-complete | missing tags: <list>') and the branch-exists guard preventing destructive overwrite. It is not a 5 because some checkpoints are implicit rather than explicit validate-then-proceed steps (e.g. no post-check after promote-to-epic, tag verification reported but not re-run); not a 3 because validation is largely present.

4 / 5

Progressive Disclosure

Section headers are clear and navigation is possible, but the skill is a monolithic single file with no bundle (no references/, scripts/, or assets/ exist), and substantial content that clearly belongs in separate shared files is inlined (User Interaction Protocol, Concurrent-agent coordination, Dialog handoffs, Signal layer, Traceability Chain). Cross-references to other skills' files (graph-invariants.md, team-workflow.md, templates) appear as bare inline code paths rather than clearly signaled links. This matches the 3 anchor 'Some structure but could be better organized; references present but not clearly signaled; content that should be separate is inline'; it is above 2 only because the in-file structure is genuinely good.

3 / 5

Total

13

/

20

Passed

Description

100%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 is exemplary: concrete third-person action statements, explicit trigger phrases with bilingual synonyms, an explicit DO-NOT-trigger boundary list, and a clear niche statement. Both 'what' and 'when' are answered unambiguously.

DimensionReasoningScore

Specificity

The description lists four concrete, distinct actions — "takes stock of the current project state, recommends the next phase skill, audits handoff entries for completeness, and runs the Closing Handoff after a successful security audit" — plus an explicit non-goal statement ("does not perform CRUD work on artifacts; every concrete change lives in the phase skill it dispatches to"). This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' and is written in third person ('Guides users'). It is not a 4 because coverage of the skill's role is comprehensive rather than leaving minor gaps.

5 / 5

Completeness

Both 'what' (four concrete actions plus explicit boundaries) and 'when' (quoted trigger phrases and an explicit DO-NOT-trigger list naming all six phase skills) are clearly and explicitly stated. This matches the 5 anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'; a 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

TRIGGER quotes natural user phrases with synonym coverage: "where do I start", "what comes next", "I am lost in the workflow", "which phase fits", plus German equivalents ("wo bin ich gerade", "wo soll ich anfangen", "was kommt jetzt") and topical phrases ("V-Model overview", "end-to-end orientation"). This is comprehensive natural-term coverage including variations, matching the anchor for 5; no common phrasing for orientation requests is missing.

5 / 5

Distinctiveness Conflict Risk

The skill has a clear niche (read-only orientation layer) and actively disambiguates from the six named phase skills via the DO NOT trigger clause, which also excludes generic 'workflow'/'process'/'next step' mentions inside an already-running phase skill. Minimal conflict risk, matching the 5 anchor; the explicit anti-trigger list is stronger than the 4 anchor's 'minor overlap risk'.

5 / 5

Total

20

/

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

skill_md_line_count

SKILL.md is long (891 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

salemaziel/digital-innovation-agents

Path

skills/dia-guide/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.