Reporting to Action
Move from checked results to a revised report and proposed actions.
Free, with limits. These skills produce AI-assisted drafts and reviews. A person who knows the program should check every output against the source documents before it is shared. The examples are fictional and written by hand; they are not real client work or test output.
Claude Code is the checked route. One skill was also checked by browser upload on a paid plan. Anthropic's help page says Free plans can use uploaded skills too, once code execution is turned on; we did not test a Free account. No M&E Studio signup or API key is needed; your Claude account and its limits are separate.
What You Will Get
- evidence.md
- report-draft.md
- review.md
- report-revised.md
- actions.md
- change-record.md
What to Provide
- One fictional case below, or equivalent readable source documents
- All component skills listed below
- Original inputs, saved artifacts and handover when resuming
Supply readable files or text. Missing evidence stays explicit; a draft or recommendation is not an approved commitment.
Start the Job
Copy the starter after obtaining its component skills below. Use one fictional case at a time. Save every intermediate file and the handover; resuming needs the original input, actual artifacts and handover in a fresh session.
Read the Starter
Reporting to action starter pack
This pack helps you complete one M&E job with free instructions and fictional attachments. Your Claude account has its own access and usage limits. Checked in Claude Code. Anthropic's help page says Free and paid plans can use uploaded skills once code execution is turned on; we checked browser upload on a paid plan only. No API key or site signup is needed.
Inputs and start
Supply reporting-to-action.md or your equivalent readable files. examples/normal and examples/difficult are separate fictional cases; never combine them. For reporting, examples/single-period tests the no-trend boundary. Browser users upload files; Code users give explicit file paths or a scoped folder. If extraction fails, provide a readable text export. This pack promises Markdown output, not Word, PDF or spreadsheet rendering.
Enable these workspace skills: progress-evidence, findings-to-actions. Also enable the review skill(s) progress-report-review from me-review. In Code load both plugins and use /me-workspace:<skill> and /me-review:<review>. In a browser upload individual skill packages and name the skill. Copy/paste fallback: paste each relevant SKILL.md in sequence with the files or text it needs; browser behavior still needs separate verification.
Starter: Complete reporting to action with my supplied documents. Use progress-evidence to write evidence.md, including coverage, arithmetic and comparison eligibility. Save the supplied draft report unchanged as report-draft.md; if none is supplied, draft one from evidence.md and label it a draft. Use me-review:progress-report-review on that draft and the input to write review.md. Revise into report-revised.md, then use findings-to-actions on supported findings to write actions.md. Record material revisions and unresolved decisions in change-record.md. Reconcile all numbers and keep period/cumulative, count/event, denominator and comparison limits consistent across evidence, report and actions. A single-period case permits no cross-period trends. Qualitative findings are not representative prevalence or causal proof. Suggested owners/dates remain proposed unless explicitly committed in the source. Return the final artifacts in editable Markdown. Separate facts, assumptions and proposed choices. Make unresolved decisions explicit.
Save and resume
Number decisions with the stage prefix (REP-D1, REP-D2) so each ID means one decision across all files. Save intermediate outputs as you go. If interrupted, use handover-template.md to state the input files/source IDs, completed files, decisions/assumptions, remaining steps and exact restart instruction. In a fresh session provide the original input, completed artifacts and handover. Re-validate inherited facts and status claims against the original sources before copying them forward. A handover is a navigation aid, not authority for approval, consent or measurement definitions. Use three evidence states: explicitly confirmed, explicitly contradicted, or unconfirmed. No supporting record means unconfirmed; it cannot justify keeping a negative status claim. If a resumed claim has no supporting record, mark it unknown rather than keeping it. Distinguish approval status of pre-existing program items from recommendations created in this draft (proposed). Do not rely on earlier chat memory or undocumented author corrections.
Expected files: evidence.md, report-draft.md, review.md, report-revised.md, actions.md, change-record.md. Check that you can open each file, follow source IDs back to inputs, distinguish proposals from commitments, and see the next decision. Human usability validation remains pending.
Required Skills and Reviews
The workflow pack does not contain these methods. Install the two plugins or download the named individual ZIPs, then follow the starter.
Try a Fictional Example
Choose a complete, difficult or single-period case separately. Never combine alternative cases.
Complete Fictional Case
Reporting to action case: Sunvale Water Committees
Fictional case. Sunvale Water Committees is an invented community water program. All organizations, locations, figures, and records below are fictional and supplied only for this exercise.
Request
Prepare a concise evidence check and report revision for the January to June 2026 review, followed by proposed management actions. The team wants to decide what to adjust before the July cycle. Keep period results separate from cumulative totals. Cite source IDs. Label proposals as proposals; no action has been approved yet.
Source SW-01: Results framework
| ID | Indicator | Reporting basis | Target |
|---|---|---|---|
| SW-I1 | Households enrolled in water committee support | Cumulative count since program start | 140 by June 2026 |
| SW-I2 | Enrolled households attending a committee meeting in the period | Period percentage: unique households attending at least one meeting during the period divided by households enrolled at period start | 60% each period |
| SW-I3 | Committees with a functioning maintenance log | Cumulative count of committees meeting the checklist at period end | 10 by June 2026 |
Source SW-02: Period data table
| Indicator | Jan-Mar 2026 period | Apr-Jun 2026 period | Prior cumulative / cohort basis |
|---|---|---|---|
| SW-I1, new enrollments | 5 households | 25 households | 80 enrolled before Jan 2026 |
| SW-I1, cumulative enrolled at period end | 85 households | 110 households | Jan-Mar end 85; Apr-Jun adds 25 |
| SW-I2, unique households attending at least one meeting | 48 of 80 at period start | 55 of 85 at period start | Denominator is enrolled households at each period start |
| SW-I3, committees meeting checklist at period end | 6 committees | 8 committees | 4 committees at Dec 2025 end; Apr-Jun adds 2 |
Source SW-03: Evaluation interview extract
Eight committee treasurers from four of the ten participating communities were purposively interviewed in June 2026. Six said that unclear responsibility for buying small repair parts had delayed at least one repair. This is a qualitative finding from a small purposive sample and is not an estimate for all committees. Interview notes do not document how many repairs were delayed.
Source SW-04: Draft report text
“Enrollment reached 110 households by June. Meeting participation rose to 65% in the second quarter, exceeding the 60% target. Eight committees now maintain a functioning log, close to the target of ten. Interviewees said unclear responsibility for small repair purchases sometimes delayed repairs.”
User task
Check the data and claims, revise the report text, and provide an evidence-linked issue list plus proposed actions with suggested owners and dates clearly labeled as proposals. Include the arithmetic for each reported figure, distinguish period from cumulative values, note the limits of the interview evidence, and identify any practitioner decision still needed. Do not invent a trend beyond the supplied periods or claim actions are commitments.
Difficult Fictional Case
Reporting to action case: Meadowline Food Access
Fictional case. Meadowline Food Access is an invented food access program. All organizations, locations, figures, and records below are fictional and supplied only for this exercise.
Request
Prepare the April to June 2026 report section and an evidence-linked management response for the July planning meeting. State what can be reported, what must be reconciled, and what actions may be proposed. Cite source IDs. Keep period results distinct from cumulative results. Do not label proposed actions as approved.
Source MF-01: Results framework
| ID | Indicator | Reporting basis | Target |
|---|---|---|---|
| MF-I1 | Households receiving at least one food voucher | Cumulative unique household count since launch | 300 by June 2026 |
| MF-I2 | Eligible households redeeming a voucher within 30 days | Period percentage: redeemed eligible households divided by eligible households issued a voucher in that period | 80% each quarter |
| MF-I3 | Distribution points submitting a complete stock log | Cumulative count at period end | 12 by June 2026 |
Source MF-02: Reconciled operations extract, exported July 3
| Measure | Jan-Mar 2026 | Apr-Jun 2026 | Note |
|---|---|---|---|
| MF-I1 new unique households served | 72 | 61 | Unique household IDs checked against prior quarters |
| MF-I1 cumulative unique households served | 180 | 241 | March cumulative plus April-June new households |
| MF-I2 eligible households issued vouchers | 100 | 90 | Period denominator |
| MF-I2 households redeeming within 30 days | 82 | 63 | Period numerator; duplicate redemptions removed |
| MF-I3 complete stock logs | 8 | 10 | Cumulative count; 2 additional points met the checklist in Apr-Jun |
Source MF-03: Draft narrative, dated June 28
“The program served 252 households cumulatively by June. Voucher redemption improved to 70%, above the 80% target. Twelve distribution points submitted a complete stock log. The team should expand to five new sites next quarter.”
No calculation sheet or source IDs accompany this draft. The operations extract in MF-02 was exported after the draft date.
Source MF-04: Field learning note
Three of five distribution-point staff interviewed in June said deliveries sometimes arrived after their planned distribution day. The interviews were convenience-selected by the field supervisor. The note does not quantify affected households, establish that late delivery caused non-redemption, or record an agreed corrective action.
Source MF-05: Planning meeting notes
- The July 12 meeting will decide whether to adjust delivery scheduling for the existing sites.
- The program director will decide whether to expand sites after reviewing cost and coverage information. Those analyses are not included here.
- No corrective action, owner, deadline, or expansion commitment has been approved.
User task
Check the report against the supplied records, revise only what can be supported, and provide an issue list and proposed management response. Show calculations and source IDs. Treat the later reconciled extract as the available current record while documenting its difference from the earlier draft. Do not convert the field note into a causal or population-wide claim. Do not claim that expansion is supported by evidence not supplied.
Single-Period Case
Single-period reporting case: Pine Harbor Learning Hubs
Fictional case. Pine Harbor Learning Hubs is an invented adult literacy program. All organizations, locations, figures, and records below are fictional and supplied only for this exercise.
Request
Prepare the April to June 2026 report section and a short list of evidence-linked next actions for the July review. This reporting request covers one period only. Cite source IDs, show the arithmetic, and label any suggested actions as proposals.
Source PH-01: Results framework
| ID | Indicator | Reporting basis | Target for Apr-Jun 2026 |
|---|---|---|---|
| PH-I1 | Learners enrolled in the period | Period count of new unique learners | 90 |
| PH-I2 | Learners attending at least 8 of 10 sessions | Period count / learners enrolled in the period | 70% |
| PH-I3 | Learning hubs submitting a complete attendance register | Period count | 6 hubs |
Source PH-02: April-June records
- 84 unique learners enrolled during April to June 2026 (source: enrollment register export dated July 2).
- 63 of those 84 learners attended at least 8 of 10 sessions (source: attendance summary checked against the 84 IDs).
- Five of six hubs submitted complete attendance registers for April to June (source: hub register checklist).
- No prior-period data or cumulative series are included in this reporting pack.
Source PH-03: Learning note
Four learners from two hubs were asked why they missed sessions. Three described seasonal work as a scheduling conflict. These were informal, purposive conversations; they are not representative and do not establish why other learners missed sessions.
Source PH-04: July review note
The program manager will review whether to offer one evening session at each hub in the next cycle. No schedule change has been approved, and no owner or deadline has been assigned.
User task
Produce the report section, a brief issue/limitation note, and a proposed action table. Show each calculation and cite the source ID. Report period values only. Do not invent a previous-period comparison, cumulative total, causal explanation, or approved management commitment.
Files for This Job
Evidence and Limits
Checked in Claude Code on fictional cases, including incomplete and unsuitable inputs, with the outputs reviewed by a second model. A browser upload check has passed for one skill (Evaluation Questions) on a paid plan. The Anthropic help page says Free plans can use uploaded skills; we did not test a Free account. Practitioner feedback is not checked yet.
Check the actual output against your source documents, especially numbers, missing data, proposed owners and approval status. Treat the result as an AI-assisted draft. Markdown and text tables are the checked output; Word, PDF and spreadsheet output are not promised. Keep each method's rating rules distinct from site rubric scores.
Source revision 5a6819f · Checked 2026-10-26