Feasible Measurement
Move from indicator review to reference sheets and a feasible M&E plan.
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
- indicator-review.md
- burden.md
- reference-sheets.md
- me-plan.md
- coherence.md
- decisions.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
Feasible measurement 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 feasible-measurement.md or your equivalent readable files. examples/normal and examples/difficult are separate fictional cases; never combine them. 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: measurement-feasibility, indicator-reference-sheets, me-plan-draft. Also enable the review skill(s) indicator-quality and me-plan-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 feasible measurement with my supplied documents. Use me-review:indicator-quality to write indicator-review.md. Use measurement-feasibility for burden.md, indicator-reference-sheets for reference-sheets.md, and me-plan-draft for me-plan.md. Use me-review:me-plan-review for coherence.md, compare every indicator ID/definition/denominator/source/frequency/role/use across artifacts, flag each inconsistency in coherence.md, then correct it in the affected file and note the change in decisions.md. Record suggested indicator revisions and unresolved decisions in decisions.md. Preserve required evidence and reporting obligations when reducing burden. Sum time by role and actual collection month, separating one-time and recurring tasks. Do not assume extra capacity or equate sessions with active weeks. When calendar counts are absent use the supplied weekly/per-event rate and a formula for total burden; any optional scenario is not a source-supported total. All-eligible confirmed-positive shares do not classify unknown individuals as negative: show missing statuses and respondent-only rates separately and keep interpretation consistent across artifacts. 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 (MEAS-D1, MEAS-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: indicator-review.md, burden.md, reference-sheets.md, me-plan.md, coherence.md, decisions.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
Feasible measurement case: Cedar Works
Fictional case. Cedar Works is an invented job-readiness program. All organizations, locations, figures, and records below are fictional and supplied only for this exercise.
Request
Create a concise indicator reference sheet and a feasible quarterly M&E plan for the July to September 2026 cohort. Show calculations, collection frequency, source, responsibility, use, and expected staff burden. Cite the source IDs. Keep essential information and flag any assumption.
Source CW-01: Program and capacity
Cedar Works served 80 participants at four sites in the July to September 2026 cohort. Each site has one facilitator. The M&E officer can spend up to 4 hours per month on this cohort's data tasks. Each facilitator can spend up to 30 minutes per week on M&E records. Staff-hour limits are available time, not a target to fill.
Source CW-02: Indicator list
| ID | Indicator | Existing definition / target |
|---|---|---|
| CW-I1 | Participants completing the course | Count of enrolled participants attending at least 10 of 12 sessions; target 60 of 80 |
| CW-I2 | Graduates in paid work 90 days after completion | Percent of graduates due for 90-day follow-up who report paid work in the reference week; target 50% |
| CW-I3 | Employers hosting a practice placement | Count of unique employer organizations hosting at least one participant placement during the cohort; target 8 |
Source CW-03: Existing records and calculation rules
- Enrollment register has 80 unique participant IDs and consent-to-contact status.
- Attendance registers list 12 sessions at each site. In this cohort, 58 of 80 participants attended at least 10 sessions.
- Forty graduates are due for a 90-day follow-up during October 2026. All 40 have valid contact permission and a follow-up status field. The follow-up form asks whether the participant did any paid work for at least one hour in the seven days before the interview. The completed follow-up records show 24 “yes,” 13 “no,” and 3 “not reached.”
- Placement log has employer ID, participant ID, and placement date. The cohort log records 10 placement events across 7 distinct employer IDs.
- Staff estimate for planning: entering or checking one site's weekly attendance register takes 15 minutes per facilitator per week. Consolidating the four site registers takes 45 minutes per site per month for the M&E officer. A follow-up call takes 8 minutes including the form. Counting unique employers from the placement log takes 30 minutes per quarter for the M&E officer.
Source CW-04: Current routine
Facilitators already maintain attendance registers weekly. The M&E officer consolidates them monthly. The 90-day follow-up is planned once for each eligible cohort, not monthly. The placement log is updated when a placement happens. Results are used in the quarterly cohort review to decide whether to adjust session scheduling or employer outreach.
User task
Review the indicators, make only justified definition changes, and produce the reference sheet and feasible plan. Show numerator and denominator rules, including treatment of the three not-reached follow-ups. Calculate observed values from the supplied records. Estimate staff burden from the stated assumptions and compare it with available capacity. Do not imply that “not reached” means “not employed.” Do not add unprovided evidence or targets.
Difficult Fictional Case
Feasible measurement case: Riverbend Skills
Fictional case. Riverbend Skills is an invented vocational training program. All organizations, locations, figures, and records below are fictional and supplied only for this exercise.
Request
Rework the program's indicator list into a usable reference sheet and quarterly M&E plan for October to December 2026. Keep the current team within its stated available hours. Identify data gaps and decisions without filling them with assumptions. Cite source IDs.
Source RS-01: Program and staff capacity
The program served 120 participants at four sites during the 2026 cycle. One facilitator works at each site. Each facilitator can spend up to 30 minutes per week on all M&E records. The M&E officer can spend up to 4 hours per month on the cycle. The proposed plan must fit these limits without assuming overtime or new staff.
Source RS-02: Requested indicator list
| ID | Indicator | Requested frequency / target |
|---|---|---|
| RS-I1 | Number attending at least 80% of sessions | Weekly; target 100 participants |
| RS-I2 | Percent employed at graduation | Monthly; target 70% |
| RS-I3 | Percent employed 90 days after graduation | Monthly; target 70% |
| RS-I4 | Percent reporting increased income | Monthly; target 60% |
| RS-I5 | Number of employers satisfied with graduates | Monthly; target 20 |
Source RS-03: Available tools and records
- Four site attendance sheets list participant ID and session dates. The cycle has 12 sessions per site. Existing end-of-cycle tally: 84 of 120 participants attended at least 10 sessions. No weekly attendance percentage is currently calculated.
- The exit form asks whether a participant has a job on the last training day. It does not define “job,” distinguish paid work from unpaid activity, or ask about hours. Completed forms are available for 96 of 120 participants; 53 answered yes.
- No 90-day follow-up tool has been approved. The current form does not record participant permission for later contact.
- No baseline or follow-up income records exist.
- Employer satisfaction is mentioned in the grant narrative, but no employer list, question, response scale, or completed record exists.
Source RS-04: Staff time estimates
- A facilitator's weekly attendance check is estimated at 20 minutes per site per week. The existing cycle already requires these checks.
- A proposed weekly cross-site attendance summary would take the M&E officer 45 minutes per week.
- The M&E officer estimates 10 minutes per participant for a new employment interview, 12 minutes for an income interview, and 8 minutes for an employer interview. These are separate activities and do not include travel or analysis.
- If a new tool is needed, allow 2 hours of M&E officer time to draft and pilot each tool. Staff estimates are planning assumptions supplied by the program, not observed timings.
Source RS-05: Reporting request
The director wants a quarterly decision meeting on December 18, 2026. The meeting can decide whether to keep the existing course schedule and what follow-up measure to pilot in the next cycle. No new staff or budget has been approved.
User task
Produce an indicator review, revised reference sheet, feasible quarterly plan, and unresolved-decision list. Show any calculation that can be supported. Distinguish measures that are feasible from those that require a new definition, permissions, tool, or later observation. Estimate the requested work's staff hours and compare it with capacity. Preserve the program's decision needs, but do not silently retain incompatible frequencies, invent targets or answers, or treat missing records as negative outcomes.
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