Getting Started

Status: Claude Code is the route that has been checked. One skill (evaluation questions) was also checked by browser upload on a paid plan. The Anthropic help page says Free and paid plans can use uploaded skills once code execution is turned on; we did not test a Free account. Practitioner feedback has not been gathered yet. These are AI-assisted drafts: a person who knows the program should check every output before it is shared.

Start here

1. Use Claude Code if you can. It is the checked route. In Claude Code, run /plugin marketplace add mestudiohq/me-review, then /plugin install me-review@me-review and /plugin install me-workspace@me-review.
2. Browser only (claude.ai)? You can upload a single skill as a ZIP file. Anthropic's help page says this works on Free and paid plans once code execution is turned on (Settings, Capabilities). We checked it for one skill on a paid plan.
3. Pick one job from the tables below and type its command, for example /me-workspace:evaluation-questions, then name your files.
4. Expect a Markdown file back. Markdown is plain text with simple marks for headings and tables; any text editor or Word can open it.
5. Check it before anyone else sees it (section 4).

Words used here: a skill is a set of instructions Claude follows for one job. A plugin is a package of skills. A handover is a short note that lets a new session continue the work. Proposed means Claude suggests it and nobody has approved it.

1. Choose the job

There are 24 jobs: 12 document reviews and 12 job skills that draft, plan or check. Each name links to its page on this site, with the start instructions, a fictional example and downloads. The full method (SKILL.md) governs if it ever differs from the short start instructions.

Eight Core Job Skills

What you need	Code invocation	Minimum starting material	Method and start instructions
Frame evaluation decisions	/me-workspace:evaluation-questions	Evaluation purpose; intended decision/use if known; program and scope	Evaluation questions
Match questions to evidence and methods	/me-workspace:question-method-alignment	Evaluation questions or purpose; population/program context; known evidence sources	Question-method alignment
Draft an evaluation TOR	/me-workspace:evaluation-tor-draft	Program description and evaluation purpose; known users, scope, timing, or constraints	Evaluation TOR draft
Document indicators	/me-workspace:indicator-reference-sheets	Indicator name or result statement; any available framework/source/definition	Indicator reference sheets
Assess measurement burden	/me-workspace:measurement-feasibility	Indicator list or measurement plan; at least one known constraint to assess	Measurement feasibility
Draft an M&E plan	/me-workspace:me-plan-draft	Program summary/results framework; indicator list or monitoring purpose	M&E plan draft
Check progress evidence	/me-workspace:progress-evidence	Progress report; a framework/definitions help check coverage; prior comparable period for trends	Progress evidence
Turn findings into proposed actions	/me-workspace:findings-to-actions	Findings or recommendations and their source; program context; any existing response	Findings to actions

Twelve Document Reviews

These review skills assess a supplied document or instrument. For cross-document checks, attach the related framework or source documents too. The linked method explains which inputs matter for that review.

What you need reviewed	Code invocation	Minimum starting material	Instructions
Logframe or results framework	/me-review:logframe-review	Logframe; proposal or ToC if checking alignment	Logframe review
Theory of Change	/me-review:theory-of-change-review	ToC document or description of causal logic	ToC review
Indicators	/me-review:indicator-quality	Indicator list and the results they are intended to measure	Indicator quality
M&E plan	/me-review:me-plan-review	M&E plan; framework and requirements help check coherence	M&E plan review
Proposal M&E section	/me-review:proposal-me-review	Proposal M&E section; relevant call or framework if checking fit	Proposal M&E review
Evaluation TOR	/me-review:tor-review	TOR or commissioning brief; program framework if checking alignment	TOR review
Survey instrument	/me-review:survey-review	Questionnaire or survey instrument; indicator definitions if available	Survey review
Sampling plan	/me-review:sampling-plan-review	Sampling plan or description of methodology; purpose/population/frame help	Sampling plan review
Baseline report	/me-review:baseline-report-review	Baseline report, study, or data summary; logframe for coverage checks	Baseline review
Progress report	/me-review:progress-report-review	Progress report; framework for coverage and prior period for comparison	Progress report review
Data-quality assessment	/me-review:data-quality-review	DQA report, methodology, or findings and the data stream assessed	Data-quality review
Evaluation report or findings	/me-review:evaluation-report-review	Evaluation report or findings brief; TOR/questions help check coverage	Evaluation report review

Four More Job Skills

These four job skills passed Claude Code checks on ordinary, incomplete and unsuitable inputs, through their own commands and seven older command names. Practitioner feedback has not been gathered yet.

What you need	Code invocation	Minimum starting material	Instructions
Compare results documents	/me-workspace:results-chain-alignment	At least two distinct design artifacts, including one results structure	Results-chain alignment
Draft a sampling plan	/me-workspace:sampling-plan-draft	Purpose/question, intended population/unit, and known sampling frame	Sampling-plan draft
Plan a data-quality assessment	/me-workspace:data-quality-planning	Indicator or data stream, intended use, and available data-flow/risk information	Data-quality planning
Plan baseline evidence	/me-workspace:baseline-planning	Indicator set, population, and exposure timing if known	Baseline planning

2. Pick an input route

Claude Code: The Checked Route

The checks used the workspace plugin and the review plugin together, with an existing Claude subscription and readable Markdown files. The local launch form is:

claude --plugin-dir <me-workspace-folder> --plugin-dir <me-review-folder>

Replace each placeholder with the folder containing that plugin on your computer. Most users should install through the marketplace commands in Start here instead. After launch, use one of the exact /me-workspace:<skill> or /me-review:<skill> invocations above. Name the specific files or one scoped folder. If you name a folder, ask the assistant to list candidate files and use only the files you identify.

The local method and workflow checks are evidence for that Code setup and editable Markdown only. They do not show that every route works with every account, provider setting, model, file type, or machine.

Browser Upload or Copy and Paste: Mostly Unchecked

The instructions describe uploading an individual skill package with readable attachments, or copying the skill's SKILL.md into a request with those attachments. On a paid account, one skill (evaluation questions) was uploaded and passed ordinary, incomplete and unsuitable checks; the four reserve skills uploaded without errors. Anthropic's help page says Free plans can also upload skills once code execution is turned on; we did not test a Free account. Other skills and copy/paste have not been verified. Do not assume that a browser can inspect a folder path, create a downloadable file, or accept a particular package format. If you try a route, confirm that the skill loaded, the input was read, and an actual Markdown artifact was created before relying on the result.

These instructions reference Claude's Skills help page and Claude Code subscription information. Check those pages for current access rules. They point to official information. The Anthropic help page says skills are available on Free, Pro, Max, Team and Enterprise plans.

No API or Extra Account Needed

These instructions do not use an API key and do not send your documents anywhere except to the Claude account you choose. The skills are free, with no M&E Studio signup. Your Claude plan and its limits are separate.

3. Start one job

1. Choose a task from the tables above and open its linked start instructions.
2. Identify the source files you intend to provide. Prefer only the documents needed for the job. Use sources you are authorized to share with the selected service.
3. State the purpose and desired artifact. Include known scope, decision, timeframe, and constraints. If a fact is unknown, say so.
4. Use the starter prompt from that skill's START.md, replacing bracketed text. Do not paste a machine path into a browser request; upload or attach the readable file instead.
5. For a complete workflow, use the relevant workflow pack's own START.md: Evaluation planning, Feasible measurement, or Reporting to action. Workflow packs name their component jobs and expected Markdown files.
6. Ask for a bounded draft when information is missing. A useful output can include explicit gaps and decisions instead of guessing.

4. Inspect the actual Markdown artifact

The accepted workflows promise editable Markdown, not Word, PDF, or spreadsheet rendering. During local checks, the actual created files were inspected; a chat summary alone was not treated as proof that a file existed. After a run:

• Confirm which .md files were actually created and open each one. If no file was created, say so; use the inline Markdown only if you can save it yourself.
• Compare key facts, figures, dates, definitions, and commitments to the supplied sources. Follow evidence IDs back to the source and verify the cited location.
• Separate facts in the source from assumptions made for drafting and proposals suggested by the assistant. Proposed owners, deadlines, actions, crosswalks, or revisions are not approvals.
• Use three evidence states: confirmed, contradicted, and unconfirmed. A missing record is unconfirmed, not proof of a negative. A source that directly conflicts with a claim is contradicted. Do not convert “not found in supplied files” into “does not exist.” Skills may also say not supplied, not assessable or decision required: these are kinds of unconfirmed, never contradicted. Use contradicted only when a supplied source directly conflicts with the claim.
• Preserve source versions and unresolved disagreements. Do not silently choose which version governs, or rewrite an approved indicator, target, or commitment. If one version is signed and a later one is not, the skills use the signed one as a proposed working version and flag the other; you decide.

Before a client, donor or manager sees an output:

• A person who knows the program reads the whole file, not only the summary.
• That person checks every figure, date and commitment against the source files.
• Every proposed owner, date and action is either approved by the right person or still marked proposed.
• The file says it is an AI-assisted draft and who reviewed it. The skill's own checklist is not a review.
• Recheck arithmetic and comparison basis. Keep period and cumulative values distinct, use matching definitions and populations, and do not describe a single period as a trend. Pre/post change alone does not establish causation.
• If your interface cannot create a file, request a Markdown response and save it manually. Do not call inline text a downloaded artifact.

5. Pause and resume with a real handover

Before pausing, save the original inputs, every actual intermediate or final artifact, and a short handover. Use the optional getting-started handover template. In a new session, provide those same source files, artifacts, and handover. Resume only from material you supply in that session; do not rely on chat memory or assume the prior workspace is available.

The handover is a navigation aid, not authority for facts or decisions. Recheck inherited claims against the original sources. Record source filenames and versions/dates, completed artifacts, unresolved choices, and the exact next step. If sources changed, flag the differences. Never upgrade a draft proposal, assumption, pending approval, or unknown status into an approved decision.

Troubleshooting

What happened	What to do
The assistant cannot identify a document or several files have similar names	Provide the specific file, version, or an explicit file list. Do not let it guess which version controls.
A file could not be read	Provide a readable text or Markdown export and state the original source and version. Do not claim the unread file was reviewed.
Information is missing	Ask for a bounded draft with “Not supplied,” “Unconfirmed,” or “Decision required” labels. Do not fill targets, budgets, sample sizes, roles, dates, or results from guesswork.
Two sources disagree	Show both with their source references and identify the decision needed. Do not silently reconcile them.
Only a chat summary appears, with no file	Ask for the expected Markdown content or save the inline response yourself. Verify the saved file's contents.
The browser route does not load or produce a usable result	Treat that route as unverified. Anthropic's help page says skills are available on Free, Pro, Max, Team and Enterprise plans; Free message limits can possibly stop a long workflow early. Use a locally available Code route only if you already have access to it, or use the skill text with readable attachments where supported.
A result seems causal	Check whether the supplied design supports attribution. If not, describe observed change, association, or the stated hypothesis without claiming causation.
Work is interrupted	Supply the original inputs, actual artifacts, and a source-checked handover when resuming.

What Has and Has Not Been Checked

Claude Code: every job skill, the four adapted reviews, the three workflows and pausing and resuming were run on fictional cases, and a separate model checked each output against a list of expected findings. Earlier failures were fixed and the affected cases rerun; not every attempt passed first time. Fresh sessions also completed the worked project from these guides alone.

Browser upload: one skill (evaluation questions) passed on a paid account, and the four newest skill ZIPs uploaded without errors. The Anthropic help page says Free plans can use uploaded skills; we did not test a Free account. Copy and paste and practitioner usability are not checked yet. Of the twelve document reviews, four were part of the latest round of checks; the other eight come from earlier releases.

The free skills have no paid API backend or site account; provider accounts and limits remain separate.

Source: M&E Studio, monitoringevaluationstudio.com. Guide and fictional attachment use is governed by the existing free-content terms; public plugin files retain their separate MIT license.

See usage and credit for how to credit M&E Studio.