html-ppt-knowledge-arch-blueprint

Open Design's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./design-templates/html-ppt-knowledge-arch-blueprint/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

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 tight, highly actionable entry-point card with concrete paths, tag rewrites, and class names, and it cleanly defers deep authoring rules to the master skill. Its one gap is the absence of a verification checkpoint after the asset-copy/rewrite step.

Suggestions

Add a verification step after Recipe A/B — e.g. 'Open index.html in a browser and confirm slide navigation (arrows/space) and theme cycling (T) work before replacing demo content.'

Include a short feedback loop for the step-3 failure mode: if the deck does not navigate, re-check that the four `<link>`/`<script>` tags were rewritten to project-local paths.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what HTML decks or templates are, and the detailed step-3 asset-rewrite warning earns its place as a real non-obvious failure mode rather than padding.	3 / 3
Actionability	Gives concrete, copy-paste-ready guidance: exact paths to copy, the specific tag rewrite from `../../../assets/...` to project-local paths, the `.tpl-knowledge-arch-blueprint` class to keep, and the `<aside class="notes">` element for speaker notes.	3 / 3
Workflow Clarity	The six authoring steps are clearly numbered and sequenced, but there is no validation/verification checkpoint — e.g. no 'open the deck in a browser to confirm assets load and navigation works' — despite step 3 warning that navigation can silently die, fitting the 'sequence present but checkpoints missing' anchor.	2 / 3
Progressive Disclosure	The card is a thin, well-organized entry point that defers detail one level deep via clearly signaled links to the master skill (`../html-ppt/SKILL.md`) and the full-decks catalog, keeping the overview appropriately light with no nested-reference chains.	3 / 3
	Total	11 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 specific about the deck's subject matter and audience but reads as a content summary of one incident rather than a capability statement. It lacks a 'Use when' trigger clause and action-led verbs, leaving it mid-tier across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming when to pick this card, e.g. 'Use when the user wants a decision-grade PM deck from an incident retro in the knowledge-arch-blueprint visual system'.

Lead with the skill's action ('Builds a decision-grade Product Management deck...') instead of the incident's content so the capability is front-loaded.

Broaden trigger terms beyond the single incident — 'incident retro', 'postmortem deck', 'learning deck', 'PM decision deck' — so the description surfaces for variations a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists concrete deck elements — 'the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups' and audiences 'engineering, SRE, leadership' — but describes the deck's subject matter rather than the skill's actions, with only an implicit 'Built as' verb, so it stops short of the multiple-explicit-actions anchor.	2 / 3
Completeness	It answers 'what' ('Built as a decision-grade product management deck for engineering, SRE, leadership') but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms ('incident retro', 'product management deck', 'root cause') but they are anchored to one specific incident and lack the common variations a user would actually say, matching the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Tying the description to 'Open Design's incident retro: the daemon-restart data bug' narrows it, but because it describes the deck's content rather than the skill's distinct mechanism it could still overlap with other retro or deck-building skills, fitting the 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 3 suspicious	Warning
referenced_paths_exist	Referenced path issues: 5 missing, 2 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/html-ppt-knowledge-arch-blueprint/SKILL.md
Commit: f2760fd

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.