Skip to content

ericrisco/rsc-harness / skills/investor-materials

investor-materials

Verified

Use when packaging or circulating the documents an investor reads outside the meeting — setting up or cleaning a data room, writing the one-pager or teaser that earns the first meeting, or drafting the recurring monthly investor update. NOT the slide narrative (that is `pitch-deck`), NOT the projection spreadsheet (that is `financial-model`), NOT round strategy and the investor pipeline (that is `fundraising`).

FileKindSize
SKILL.mdskill md12.4 KB
evals/README.mdmarkdown1.2 KB
evals/cases.yamlconfig4.7 KB
references/dataroom-checklist.mdmarkdown4.6 KB
references/update-and-onepager-templates.mdmarkdown4.9 KB
scripts/verify.shexecutablescript6.0 KB

evals/README.md

View on GitHub
# Evals — investor-materials

`cases.yaml` is read by the repo's skill-eval harness. `should_trigger` and
`should_not_trigger` measure routing precision: each `should_trigger` prompt must load
`investor-materials`, and each `should_not_trigger` prompt must instead route to the named
sibling (`pitch-deck`, `financial-model`, `fundraising`, `cold-outreach`, `unit-economics`) —
they encode the boundaries between packaging documents and building the story, the numbers, or
the round. The `capability` case is a scenario scored by a judge model against its `must_include`
rubric: it feeds the prompt, lets the skill generate the data-room index / one-pager / update
bundle, and checks the rubric points are met (8 numbered categories, the dated/versioned naming
example, the 7 one-pager blocks with a specific ask, the 6 update sections with a metrics table
and named asks, and correct routing of deck/model work to siblings). Run it through the
repository's standard eval command (see the repo root). The structural lint in
`../scripts/verify.sh` is complementary — it checks the generated artifacts mechanically; the
capability eval judges framing and metric selection, which the script deliberately does not.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall