Skip to main content
affpapa.org
RU EN
skill CX Codex

mel-framework-citation — Claude Code skill: setup and features

Enforces evidence-based citation standards for MEL and SRHR deliverables. It flags outdated framework editions and formats references by audience level.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add gasserane/personal-skills --skill mel-framework-citation -a claude-code
Open on GitHub

What mel-framework-citation does

The skill standardizes evidence citations across monitoring, evaluation, and learning (MEL) documents. When drafting theories of change, indicator matrices, or evaluation designs, it verifies references against recognized releases. These benchmarks include Mayne's 2019 contribution analysis, the 2019 OECD evaluation criteria, and the 2023 WHO/UNFPA sexual health indicators. Outdated versions trigger explicit warning flags in the output.

Reference formatting adjusts according to audience tier. Tier 1 working briefs keep the narrative focused on analytic actions while appending evidence-base blocks to each section. Tier 2 publications receive formal inline citations with author surnames, publication years, and titles. Vague attributions are rejected. Unsupported claims receive data-gap notices.

Indicator frameworks must disaggregate data across four mandatory dimensions: age cohort, gender identity, disability status, and geographic stratum. Omitting any dimension causes the skill to mark the indicator set as incomplete.

What it helps with

  • verify methodology editions against verified benchmarks
  • format reference placement based on target audience tiers
  • flag unsupported assertions using the data-gap protocol
  • audit indicator frameworks for mandatory demographic disaggregation

Example prompts for the agent

  • Review the evaluation design and format citations for a Tier 1 working brief
  • Draft programme indicators with mandatory disaggregation by gender identity, age, and disability
  • Check the theory of change draft for outdated methodological frameworks

How to install mel-framework-citation

1Skills CLI (Vercel)

npx skills add gasserane/personal-skills --skill mel-framework-citation -a claude-code

2Manually: put the files in place

~/.claude/skills/mel-framework-citation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/mel-framework-citation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about mel-framework-citation

How to install mel-framework-citation in Claude Code?

Run npx skills add gasserane/personal-skills --skill mel-framework-citation -a claude-code.

What deliverables should use mel-framework-citation?

Apply it to evaluation designs, theories of change, indicator systems, and donor reports in the MEL or SRHR domains. It is not intended for general correspondence or non-evaluation writing.

What are the disaggregation requirements for indicators?

All indicator frameworks must include disaggregation by age cohort, gender identity, disability status, and geography. Missing any of these four strata results in a quality flag.

Similar skills

All skills for Writing and docs →
grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. 1,219,756installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs handoff Matt Pocock Creates a handoff document from the current conversation so another agent can continue the work. Use it when a task moves to a new session or agent. 1,038,491installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. 990,453installs domain-modeling Matt Pocock This skill sharpens project terminology, maintains GLOSSARY.md, and records selected architecture decisions in ADRs. Use it while the domain model is changing. 876,391installs

From the same set22

daily-brief Builds a compact morning brief from priorities, calendar items, overdue work, pending decisions, and an energy check. CX Codex +1 682installs decision-memo Turns a pending choice into a written memo: context, options, a recommendation, risks and reversibility. Useful when a decision needs a record. CX Codex +1 664installs video-content-analysis Turns a local video into a transcript, frames, manifest, and short summary. It fits focus groups, webinars, training sessions, and recorded meetings. CX Codex +1 662installs power-bi-build Scaffolds IPPF-branded Power BI projects and writes DAX measures directly to .pbip models. Requires Power BI Desktop and the pbi CLI. CX Codex +1 658installs indicator-designer Designs MEL/SRHR indicators against IPPF, UNFPA, and UNAIDS standards. Useful for results frameworks, KPI sets, and measurement plans. CX Codex +1 656installs researcher Synthesizes evidence briefs for complex MEL and SRHR programs. Prepares research summaries between the initial assessment and planning phases. CX Codex +1 654installs ane-voice This skill reviews AI-written prose and reshapes it to Ane’s IPPF MEL/SRHR voice while keeping the argument rigorous. Use it for focused editorial passes. CX Codex +1 654installs ann Acts as a convener for evaluation and analytical workflows. Organizes subagents and structures execution plans based on domain standards. CX Codex +1 653installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor