CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

66%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 content is a highly actionable, well-sequenced pitch-deck builder with an explicit, checklist-driven Delivery Gate workflow and sound one-level-deep deferral to the pptx base skill. Its chief weakness is conciseness: heavy repetition of the same VC-domain rules (hockey-stick, Use-of-Funds, '$'-strip) and coaching of fundraising concepts Claude already knows inflate the token budget without adding executable value.

Suggestions

Deduplicate the repeated rules: state the hockey-stick axismin=0 rule, the 4-bucket Use-of-Funds convention, and the single-quote '$' escape once in their primary sections, then reference them ('→ see §...') from the ship-check, Gate 5b, Gate 6, and Known Issues instead of restating each.

Trim VC-psychology coaching that Claude already knows (e.g., 'VCs will not trust a single number', 'read co-founder, passionate in 0 seconds', 'student project') down to the operational QA check it motivates, keeping the grep/query condition and dropping the rationale prose.

Move the executable Gate 6 bash script and the per-recipe geometry/coordinate tables into a references/ file (e.g. GATES.md, RECIPES.md) and point to them from SKILL.md, so the overview stays lean while keeping the full operational detail one level deep.

DimensionReasoningScore

Conciseness

The ~810-line body is noticeably verbose: it repeatedly coaches fundraising domain knowledge Claude already has (hockey-stick y-axis explained 4+ times, Use-of-Funds 3+ times, '$'-strip 3+ times, VC-psychology asides like 'VCs read co-founder, passionate in 0 seconds'), fitting 'Noticeably verbose; several unnecessary explanations or padded sections' over the 'some unnecessary explanation' of 3.

2 / 5

Actionability

Most recipes give fully executable, copy-paste officecli commands with complete props and real values (Cover, Problem batch JSON, Market/Traction charts, Ask pie), plus executable QA one-liners and the full Gate 6 script; a few abbreviate with '# Repeat for cards 2/3' (x-positions and grid math still given) or defer a full batch to pptx v2 base — minor gaps keeping it at 4 rather than 5.

4 / 5

Workflow Clarity

The build path is a clearly sequenced, fragile process (stage diagnosis → vertical template → 10-recipe arc → Delivery Gate) with explicit validation checkpoints and feedback loops — 'Only proceed when validation passes', Gate 5b 'If ANY defect — REJECT', Gate 6 PASS/REJECT/WARN with exit 1, fix-and-re-validate — plus a 9-point Gate 5b checklist and 6-point Gate 6 checklist.

5 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is well-sectioned with clear headers and relies on well-signaled, one-level-deep deferrals to the sibling base skill ('→ see pptx v2 §X'), which is genuinely good disclosure toward that base — but bulk content that could be split into reference files (arc templates, recipe geometry tables, the Gate 6 script) is inlined, a minor organization gap landing it at 4.

4 / 5

Total

15

/

20

Passed

Description

95%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 a strong, trigger-rich statement that explicitly answers what and when, with comprehensive natural-language triggers and explicit negative routing against the sibling pptx skill. Its only soft spot is framing capabilities as triggers/identity rather than a comprehensive action-verb list, which caps specificity at 4.

DimensionReasoningScore

Specificity

Names the domain richly and several concrete specifics (output 'a single .pptx', 'scene layer on top of officecli-pptx — inherits every pptx v2 rule', explicit route-away exclusions), but it frames these as triggers/identity rather than a comprehensive list of distinct action verbs (extract/fill/merge/convert), so it sits at 4 rather than 5 and above the 1-2-actions anchor of 3.

4 / 5

Completeness

Clearly answers both 'what' ('building a fundraising / investor pitch deck... Output is a single .pptx') and 'when' with an explicit 'Use this skill when...' clause plus a concrete 'Trigger on:' list and negative routing, fitting the both-answered-with-concrete-trigger-phrases anchor.

5 / 5

Trigger Term Quality

Exhaustive natural-language coverage — 'pitch deck', 'investor deck', 'Series A/B/C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation', plus 'convertible note' and 'SAFE round' synonyms — matching what a user would actually say, with the .pptx file context included.

5 / 5

Distinctiveness Conflict Risk

Clear niche (fundraising only) with active disambiguation — 'DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base' — minimizing conflict risk against the most likely sibling skill.

5 / 5

Total

19

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.