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

70%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.

A highly actionable, workflow-driven skill with exceptional validation gates and feedback loops, but it is a monolithic single file with notable internal duplication and several recipe blocks that defer execution to an external skill rather than standing alone.

Suggestions

Deduplicate the Gate 5b section — keep either the bullet checklist or the '(a)–(f)' instruction list, not both — and remove the repeated 'assumptions panel is load-bearing' paragraph in recipe 9.

Move the 5 赛道 arc templates and/or the Gate 6 script into a references/ file, keeping SKILL.md as an overview with one-level-deep pointers, which would also cut token load.

Inline the full batch block for recipes 3 and 6 (currently comment stubs pointing to pptx v2) or consolidate them into a single explicit 'see base skill' pattern so every recipe is either executable or clearly deferred by design.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of concept padding, but contains real redundancy — the Gate 5b checklist is stated twice (bullet list, then the '(a)–(f)' list repeating the same checks), and 'a 4-year plan without visible assumptions reads as aspirational' appears twice within recipe 9 — plus inline version pins ('confirmed on v1.0.63') that a deprecated/old-patterns section would isolate. This fits anchor 3 (mostly efficient, could be tightened) better than anchor 4.	3 / 5
Actionability	Most recipes give copy-paste-ready officecli add/batch blocks with real coordinates, values, and QA greps (cover, problem, why-now, market, traction, financials, ask, pipeline, competitive table), but recipes 3 and 6 and the milestone-timeline block are comment stubs deferring to the external pptx v2 file ('Full batch block → see pptx v2 §(c)'), leaving minor executable gaps — anchor 4.	4 / 5
Workflow Clarity	A clear ordered sequence (read pptx base → stage diagnosis 'before writing a single command' → pick pattern → apply recipe → run Gates) with explicit executable validation (Gates 1–6, REJECT/exit 1 on failure) and feedback loops for error recovery (Gate 2b fix instruction: re-issue with single quotes; Gate 6 'fix before delivering') — anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), so all ~800 lines live in one monolithic SKILL.md; cross-references to the external base skill are clearly signaled ('→ see pptx v2 §X'), but content that would conventionally be split out (5 vertical arc templates, 12 slide recipes, the Gate 6 script) is fully inlined — anchor 3.	3 / 5
	Total	15 / 20 Passed

Description

90%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.

An excellent description with explicit trigger guidance, comprehensive natural keywords, and strong conflict-avoidance routing to the base skill. The only weakness is that the 'what' side relies on one action plus inherited-capability naming rather than enumerating the skill's own concrete capabilities.

Suggestions

Enumerate one or two of the skill's own concrete actions (e.g., 'diagnoses funding stage and generates the 10-slide VC narrative arc') so the 'what' matches the strength of the 'when'.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete deliverable ('building a fundraising / investor pitch deck', 'Output is a single .pptx') and lists inherited traits ('visual floor, grid, palettes, connector canon, Delivery Gate'), but those inherited traits are not actions this skill itself performs — matching anchor 3 (1-2 concrete actions, not comprehensive) rather than anchor 4, which expects the skill's own several actions enumerated.	3 / 5
Completeness	It explicitly answers both 'what' (build a fundraising pitch deck, output a single .pptx, scene layer on officecli-pptx) and 'when' ('Use this skill when the user is building…' + an explicit 'Trigger on:' list), plus a when-not clause — the anchor 5 pattern with concrete trigger phrases.	5 / 5
Trigger Term Quality	Ten natural trigger phrases ('pitch deck', 'investor deck', 'Series A deck' through 'raising capital', 'term sheet presentation') plus round-type synonyms (seed, Series A / B / C, convertible note, SAFE) and the '.pptx' extension give comprehensive coverage of terms a user would naturally say — anchor 5.	5 / 5
Distinctiveness Conflict Risk	'DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base' carves out a clear fundraising niche and actively routes overlapping cases away, giving minimal conflict risk — anchor 5.	5 / 5
	Total	18 / 20 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: 5bd4f1a

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.