mel-framework-citation
MEL Framework Citation
Applies Ane's non-negotiable MEL/SRHR citation standard from CLAUDE.md. Generic framework references are a quality failure. This skill prevents that. Citation rigour is constant across audience tiers; placement varies by tier per CLAUDE.md "Audience tiers and register".
When to use
Trigger whenever the output is an MEL or SRHR deliverable: theory of change, evaluation design, indicator framework, donor report, programme analysis, decolonial or feminist evaluation note, OECD-DAC review, participatory method recommendation, SRHR rights analysis.
Do not trigger for non-MEL documents, general correspondence, or requests unrelated to evaluation/SRHR.
Required behaviour
Every MEL/SRHR claim must carry author surname, year, and specific document title. Minimum. Section or page when available. The rigour rule is tier-invariant; the placement rule is tier-specific (see below).
Citation placement by audience tier
Read the audience tier from the prompt's Standing instructions block (passed by Ann via Vi). If the tier is not stated, default to Tier 1 / colleague.
- Tier 1 working brief (default). In the running text, name the analytic move, NOT the framework. Write "tested whether the programme caused the outcome by ruling out rival explanations," not "applied Mayne (2019) revisited contribution analysis." At the end of each section, append
**Evidence base:** [author (year) full title, section, hyperlink]; [next source]. The full source list also appears in the## Sourcessection at end of document.
More from gasserane/personal-skills
journal-reflection
Guide Ane through structured reflection at end of day, end of week, after a decision, or after encountering new learning material. Use when the user says "journal", "reflect on today", "weekly review", "what did I learn", "after-action review", or references writing to the MELdigitalgarden vault. Produces Obsidian-compatible markdown; writes directly to the vault when filesystem MCP is connected, otherwise returns content for manual save.
36evidence-synthesis
Conduct a rigorous rapid evidence assessment or systematic-lite literature review for MEL/SRHR questions. Use when Ane asks for "evidence review", "literature review", "evidence synthesis", "REA", "what does the evidence say", "what do we know about", or similar. Produces a structured brief with question framing, method, findings by theme, confidence grading, and implications for programme or evaluation design. Does not invent citations.
34daily-brief
Produce a scannable morning briefing for Ane (Senior MEL/SRHR Specialist at IPPF). Use when the user asks for "daily brief", "morning briefing", "start of day", "what's on today", "plan my day", or similar. Assembles today's priority, calendar, overdue items, pending decisions, and an energy check. Operates on user-provided inputs by default; richer when calendar/email MCP servers are connected.
32decision-memo
Draft a structured decision memo for Ane. Use when the user asks for a "decision memo", "decision doc", "options paper", "recommendation brief", or equivalent. Produces a scannable document with context, options, recommendation, risks, and reversibility. Applies Ane's CLAUDE.md writing style automatically.
31vi
Vi — HR Specialist and Execution Orchestrator for MEL/SRHR work. Receives an approved plan from Ann (or directly from Ane), designs the specialist roster, spawns specialists as subagents, reviews their outputs, compiles the final product, and returns it. General-purpose — invoked by Ann via Agent tool, or directly by Ane when a plan is already approved.
30li
Li — Knowledge Manager for Ane's library and MEL Wiki. Use when Ane needs to catalog, retrieve, or reorganize documents in the personal knowledge library, or query/maintain the MEL Wiki. Handles INGEST, QUERY, and LINT operations. Does not answer domain questions — retrieves and organizes knowledge for other agents and Ane.
30