officecli-pitch-deck

Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate). DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

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 and workflow-clear, with executable recipe blocks and a rigorous gated validation process. Its main limits are length/repetition across sections and a monolithic single-file structure with no bundle files to aid navigation.

Suggestions

Consolidate the repeated axismin=0 / hockey-stick guidance into one canonical location and cross-reference it, eliminating the five-plus redundant restatements.

Split the recipe catalog and/or Delivery Gates into reference files (e.g. references/recipes.md, references/gates.md) with brief inline pointers, to move progressive disclosure toward one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence (no 'what is a PDF' filler), but at ~800 lines it repeats cross-cutting rules — the axismin=0 / hockey-stick point appears six times and the zsh $-strip failure mode three times — so it is mostly efficient but could be tightened rather than lean.	2 / 3
Actionability	Recipes give fully executable officecli commands, complete batch JSON heredocs with exact x/y/width/height, derived grid math, and copy-paste-ready blocks with concrete QA one-liners — no pseudocode placeholders.	3 / 3
Workflow Clarity	A clear ordered process (stage diagnosis → pattern → recipe → Delivery Gates 1–6) with explicit validation checkpoints and feedback loops ('If ANY defect — REJECT; do not deliver until fixed', re-issue single-quoted on Gate 2b failure) for a batch operation.	3 / 3
Progressive Disclosure	It signals one-level-deep references to the pptx v2 base ('→ see pptx v2 §X'), but there are no bundle files (references/scripts/assets absent) and all pitch-specific recipes, patterns, and gates sit inline in a monolithic ~800-line file rather than being split into separate, navigable files.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, trigger-rich, and complete with explicit what/when guidance plus clear negative routing. Its only weakness is the second-person 'Use this skill when...' framing rather than the rubric's preferred third-person voice, which caps specificity.

Suggestions

Rewrite the opening in third person ('Builds fundraising/investor pitch decks as a single .pptx...') to satisfy the rubric's voice guideline and recover the specificity point.

Consider trimming the inherited-rule list (visual floor, grid, palettes, connector canon, Delivery Gate) since the body already elaborates it; the description earns more from trigger density than from enumerating internals.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions (round types, single-.pptx output, scene-layer inheritance of pptx v2 rules), but opens with second-person 'Use this skill when the user is building' rather than the third-person voice the rubric requires ('Builds', 'Generates'), which the voice guideline penalizes by reducing specificity by one.	2 / 3
Completeness	Clearly answers both what (building a fundraising/investor pitch deck, single .pptx output, scene layer over officecli-pptx) and when (explicit 'Use this skill when...' clause plus a labeled trigger-on list).	3 / 3
Trigger Term Quality	An explicit trigger list covers natural user phrasings — 'pitch deck', 'investor deck', 'Series A/B/C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation' — giving strong coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear fundraising niche with distinct round-based triggers plus an explicit negative route ('DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base') makes wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (809 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: Team-Commonly/commonly
Path: backend/commonly-bundled-skills/officecli/skills/officecli-pitch-deck/SKILL.md
Commit: 69b6005

Reviewed: about 18 hours 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.