CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-ppt-knowledge-arch-blueprint

OpenDesign'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

63%

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 ./plugins/_official/examples/html-ppt-knowledge-arch-blueprint/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 lean, concrete entry-point card: it gives exact file paths, two explicit asset-fixing recipes, and clear template constraints without padding. Its weaknesses are the absence of any verification step after the fragile asset-URL rewrite and that every referenced file lives outside the shipped bundle, making the progressive-disclosure chain dead ends in isolation.

Suggestions

Add a validation step after Recipe A/B, e.g. "Open index.html and confirm arrow-key navigation and animations work; if styles are missing, re-check the four rewritten link/script paths."

Either bundle the referenced master-skill rules and template files (references/, assets/) with this skill, or inline the minimal subset needed so the card is self-sufficient when the sibling paths are unavailable.

Show the literal before/after `<link>`/`<script>` tag lines for Recipe A so the rewrite is copy-paste ready instead of requiring the executor to reconstruct them.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — it explains only non-obvious, project-specific knowledge (why the parent-relative asset URLs 404, how to rewrite them). Minor over-explanation: step 3 enumerates the same four asset files three times across the intro, Recipe A, and Recipe B, which could be tightened. Not anchor 5 for that reason; well above anchor 3's "some unnecessary explanation".

4 / 5

Actionability

Guidance is highly concrete: exact source paths to copy, the two explicit recipes for rewriting the four `<link>`/`<script>` tags, the theme swap mechanism (`<link id="theme-link">`, `T` cycle), and the `.tpl-knowledge-arch-blueprint` class constraint. It falls short of anchor 5 only because no literal before/after tag lines or copy-paste commands are shown, leaving the executor to construct the exact replacements.

4 / 5

Workflow Clarity

A clear, well-ordered 6-step sequence (read master skill → copy template → fix asset URLs → pick theme → replace content → speaker notes) with the key failure mode (dead navigation from unresolved assets) called out, but there are no validation checkpoints — no step verifies the rewritten deck actually loads and navigates. Anchor 3 (steps listed, checkpoints missing) fits better than anchor 4, which requires most checkpoints present.

3 / 5

Progressive Disclosure

As an overview card the structure is good: clear sections and explicitly signaled one-level references to the master skill, full-decks catalog, and template folder. However, none of the referenced files ship with this bundle — there are no references/, scripts/, or assets/ directories, and paths like `../html-ppt/SKILL.md` and `design-templates/html-ppt/templates/.../index.html` resolve outside it — so the disclosed material is unreachable from the skill alone. Scored against the actual bundle structure, this sits at anchor 3: good structure, but the references cannot be navigated as bundled.

3 / 5

Total

14

/

20

Passed

Description

48%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 clearly conveys the deck's subject and audience, but it reads as a content synopsis of the artifact rather than a statement of what the skill does or when to invoke it. It lacks any trigger guidance and misses the most natural search terms (postmortem, retrospective).

Suggestions

Rewrite the description around the skill's actions in third person, e.g. "Builds a decision-grade product management deck..." followed by what it produces (slide plan, written slides, visual direction, speaker notes, critic pass).

Add an explicit trigger clause: "Use when the user asks for an incident retro, postmortem, or retrospective deck, or wants a learning deck from an incident writeup."

Include common synonyms such as "postmortem", "retrospective", and "incident review" so the skill matches the phrasings users actually say.

DimensionReasoningScore

Specificity

The description names a concrete subject ("the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups") but describes the deck's content rather than the skill's actions; the only action phrasing is the generic "Built as a decision-grade product management deck". It is above anchor 1 (not purely abstract) but below anchor 3, which requires 1-2 concrete actions the skill performs.

2 / 5

Completeness

The "what" is reasonably clear (a decision-grade PM deck about a specific incident), but there is no "when" — no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 because the "when" is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Some relevant natural terms are present ("incident retro", "data bug", "root cause", "product management deck"), but the most common user phrasings for this task are missing: "postmortem", "retrospective", "incident review", "slides". This matches anchor 3 (relevant keywords, missing common variations) rather than anchor 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

The named incident subject ("OpenDesign's incident retro") and template framing give it a clear niche with minimal conflict risk, but "product management deck" for "engineering, SRE, leadership" overlaps with a family of sibling deck-authoring skills, matching anchor 4 (mostly distinct, minor overlap with closely related skills) rather than anchor 5's fully distinct triggers.

4 / 5

Total

12

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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

plugins/_official/examples/html-ppt-knowledge-arch-blueprint/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.