estimation-stinger

Software estimation and forecasting specialist. Covers relative-sizing frameworks (story points, Fibonacci, T-shirt sizing, Planning Poker), the NoEstimates movement and its evidence base, the planning-fallacy literature explaining why estimates are systematically wrong, and cycle-time / throughput-based probabilistic forecasting (Monte Carlo simulation, percentile-based delivery predictions). Invoke when the user says "our story points mean nothing", "should we use NoEstimates?", "how do I do T-shirt sizing for a roadmap?", "we need a 90% confidence delivery date", "explain Monte Carlo to my PM", "why are our estimates always wrong", or any question about sizing, forecasting, or the NoEstimates debate. Do NOT invoke for sprint cadence design, Jira/Linear tool configuration, or team-capacity math -- those belong to the team's agile process or tooling domains.

Jump to install

Repository: legioncodeinc/the-apiary
Last source activity: July 1, 2026 at 09:19
Detected SKILL.md language: English
Stars: 2
Forks: 1

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/legioncodeinc/the-apiary --skill estimation-stinger

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

19 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

honeycomb-design

Use this skill to generate well-branded interfaces and assets for Honeycomb (shared AI agent memory, a Legion Code × Activeloop product), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

2026-07-02

adr-writing-stinger

Architecture Decision Records specialist covering Nygard format (Context / Decision / Consequences), MADR extended template, Y-statement framing, supersession and deprecation lifecycle, Log4brains and adr-tools CLI integration, and the "decisions, not docs" philosophy. Use when authoring a new ADR, superseding an existing decision, auditing the ADR log, setting up Log4brains, or onboarding a team to ADR practice. Do NOT use for general knowledge-base authoring (library-worker-bee), code entity extraction (wiki-worker-bee), or security review of the decisions themselves (security-worker-bee).

2026-07-01

affiliate-referral-program-stinger

Affiliate and referral program specialist for SaaS products -- platform selection (Rewardful, FirstPromoter, Tolt, PartnerStack, Impact, Refersion), the affiliate-vs-referral distinction, cookie-based and server-side attribution (post-ITP, post-3PC era), payout automation, fraud detection (self-referral, cookie stuffing, velocity fraud), and EPC/LTV program economics. Invoke when the user says "set up an affiliate program", "which affiliate platform should I use", "Rewardful vs FirstPromoter", "my attribution is broken in Safari", "referral program fraud", "EPC or LTV for our program", "20% recurring commission", "postback tracking setup", or "PartnerStack vs FirstPromoter". Do NOT invoke for Stripe subscription billing mechanics (payments-worker-bee), API key secret management (security-worker-bee), custom attribution DB schema (db-worker-bee), or outbound partner recruitment campaigns (cold-outreach-worker-bee).

2026-07-01

View all from this repository

Estimation Stinger

Procedural arsenal for estimation-worker-bee, the Legion AI Army's authority on software estimation and probabilistic delivery forecasting.

This stinger encodes:

The canonical relative-sizing frameworks: Fibonacci story points, T-shirt sizing, Planning Poker, and when each applies.

The NoEstimates movement: Vasco Duarte's throughput-as-forecast argument, prerequisites, and the honest evidence gap (no controlled RCTs).

The planning-fallacy literature: why expert estimators are systematically wrong, the inside-view / outside-view distinction, and Kahneman/Tversky/Flyvbjerg's recommended remedy (reference class forecasting).

Monte Carlo simulation: how it works, what data it needs, the 2026 free tooling landscape, and practical setup for teams with cycle-time history.

The five-category dysfunction diagnosis that tells you WHICH technique to recommend before you recommend anything.

It does NOT encode sprint planning ritual design, Jira/Linear configuration, team capacity planning formulas, or vendor procurement.

When this stinger applies

Load when estimation-worker-bee is invoked. Typical user phrases: