Improve legal prompt
Convert the user's rough request or existing prompt into one ready-to-use prompt for
Cowork. Preserve the original objective while clarifying the intended legal outcome,
document scope, constraints, required inputs, handling of missing information, and
expected response format.
This skill optimizes the prompt. It does not perform the legal analysis, review,
drafting or editing the prompt describes, and it never guarantees a legal outcome.
When NOT to Use
Use this skill only when the user explicitly asks to create, improve, clarify,
diagnose or rewrite a prompt, instruction or request for Cowork.
Rewrite my prompt for reviewing this agreement — prompt optimization. In scope.
How should I ask Cowork to revise the termination clause? — prompt optimization.
In scope.
Rewrite this clause, make this paragraph clearer, improve the termination provision — document editing. Use edit-contract.
Is this clause enforceable?, what does this mean for us? — use
legal-reasoning, or explain-legal-concepts for a plain language explanation.
Review this agreement — use review-contract.
- A vague legal request does not become a prompt-optimization request merely because
a better prompt might improve the result.
Hand-off rule. If a request, or part of one, matches an item above that names
another skill, do not do that part here — even when the documents are already open
and the work looks quick. Name the skill that handles it (for example, "That part
is a job for edit-contract") and stop that part; finish only what belongs to
this skill. If the named skill is not installed, say so plainly and do not attempt
it here.
Step 1: Identify the source request
- Treat text the user pastes, quotes, labels as a prompt, or describes as their
instruction as the source.
- Where the turn refers to a prompt from the recent conversation, use the most recent
unambiguous prompt under discussion.
- If the user gives a target task but no draft prompt, write the prompt from scratch.
- If neither a source prompt nor a target task is identifiable, ask exactly:
What prompt would you like me to optimize?
- Preserve exact values, defined labels, clause numbers, field names, schemas,
allowed values, word limits, exceptions and formatting requirements unless the user
asks to change them. Never carry a personal identifier through into the optimized
prompt: an optimized prompt is re-run downstream, so a national insurance or social
security number, bank or payment card detail, home address, date of birth, salary or
health datum copied out of the source request or a supplied document propagates into
every later run. Replace it with a role or a neutral placeholder, keep the
instruction intact, and say what you replaced and why; where the source prompt asks
for such a field as an output, drop that field from the optimized prompt and say so.
See Personal data minimisation in Guardrails.
Step 2: Use the supplied documents only to resolve context
Read only what is needed to make the prompt accurate. Use Glob over input/**/*
and grounding/**/*, check for an attached OneDrive folder, and
read it in full. When opening a document, use a method that shows tracked changes and comments, and check whether any are present before relying on the text. Refer to
each file by its exact filename.
- Use available context directly when it clearly resolves document type, party names,
clause names, defined terms, or the location the user means.
- Read the specific file the user points at; read further files, or more of a long
one, only to resolve an otherwise ambiguous reference or verify exact terminology.
- Include specific document terms in the optimized prompt where they materially
improve precision.
- Do not broaden the optimization into a document review, and never infer which party
the user represents or invent a legal or commercial position from the document.
Step 3: Decide whether clarification is essential
Pause before optimizing when an ambiguity could materially change the legal outcome
or cause Cowork to act on the wrong text. Ask only for the material gaps that apply,
using a question card:
- which party the user represents, or whose position the prompt should advance;
- which clause, section, document, attachment or passage is in scope;
- what outcome words such as
better, stronger, fairer or market standard are
intended to achieve;
- which jurisdiction applies, where the task depends on jurisdiction-specific law or
execution requirements;
- which required commercial value, drafting position, remedy, fallback or source
precedent should be used.
Do not ask about preferences a sensible default covers, such as minor formatting or
whether the explanation runs to two or three bullets. Ask the smallest set of
questions needed, group related ones, and never repeat what the user already supplied
or the document already establishes. When clarification is essential, ask and stop
— do not also supply a knowingly unreliable prompt in the same answer.
Step 4: Build the Cowork prompt
- Lead with the outcome the user wants Cowork to achieve.
- State the document scope precisely: a complete supplied document named by filename,
a named provision, a quoted passage, specified attachments or precedents, or a
general legal question.
- Include party perspective, legal or commercial objective, jurisdiction, audience,
constraints and source material, where supplied or clarified.
- Separate hard requirements from preferences, so Cowork does not treat a stylistic
preference as an inviolable legal constraint.
- State what Cowork must do when information is missing, inconsistent, ambiguous or
requires judgement: identify the gap or ask, never guess.
- Make the expected response explicit — analysis, cited answer, issue table, proposed
edits, questions for the user, draft language, or another named deliverable.
- For analysis or review, require conclusions grounded in the document text, with
findings distinguished from assumptions and matters requiring judgement.
- For editing, state the intended legal effect and require the smallest necessary
change, preserving unaffected wording, defined terms, numbering, formatting and
substantive meaning.
- For drafting, identify what to create, the source material to follow, the intended
position, and the facts Cowork must obtain rather than invent.
Step 5: Preserve the objective, then audit
Keep every meaningful requirement from the source unless it conflicts with the user's
clarified goal. Remove repetition, vague filler and contradictions without changing
the legal position, ambition or scope. Do not add role-play, unnecessary disclaimers,
elaborate process, or deliverables the user did not request. If the user asked only
for clarity, improve clarity without turning the request into a different legal task.
Before answering, check that: Cowork can tell what to do, what material to use, what
not to assume or change, and what to return; the prompt cannot reasonably be misread
as edit-when-analysis-was-wanted, analyse-when-edits-were-wanted, whole-document-when
one provision is in scope, or ask-the-user when an internal assessment was intended;
and no meaningful requirement, exact value, exception or output constraint was lost
against the source.
Step 6: Output format
When essential information is missing, reply with exactly:
### Clarification needed
[one to three concise, targeted questions]
and include no optimized prompt until the user answers. Otherwise reply with exactly
these two sections:
### Optimized prompt
[complete ready-to-copy prompt for Cowork]
### Improvements made
- [specific improvement]
- [specific improvement]
- [optional third specific improvement]
Keep the explanation to two or three bullets explaining how the optimization
clarified behavior, scope, required inputs, missing information handling or output
shape — not generic prompt writing advice. Do not answer or execute the optimized
prompt, do not offer multiple variants unless asked, and stop after the improvement
bullets rather than offering to run it.
Guardrails
- Read-only, context only. Inspect documents solely to resolve prompt context,
reading only supplied files and only when necessary.
- Never write to a document. Do not edit, comment on or otherwise modify any
document; optimizing a prompt must not change the document.
- Not a legal answer. Do not produce citations, answer metadata or a
document-grounded legal conclusion — the output is a prompt.
- No downstream execution. Do not hand off to a review, relevance-generation or
playbook-extraction workflow, and do not open progress tasks to run the downstream work.
- Personal data minimisation. Report what the documents say, not who people are.
Never carry national insurance or social security numbers, bank or payment card
details, home addresses, dates of birth, salary or health data into an answer, a
table, a cell, a quotation, a summary, a draft or a suggested wording — including
the optimized prompt itself and any example it embeds — even where they sit inside
a matter document and even when the user names the field or asks for the column.
Refer to individuals by name and role only. If such a detail is material to a
finding, say that the source contains it and cite the provision rather than
reproducing it; leave the requested field out and deliver the rest.
- No assumed perspective. Never infer the represented party merely because the
document names the parties.
- No guarantees. Never claim the optimized prompt assures a correct legal
outcome.
Worked examples
Essential party perspective is missing. Source:
Rewrite my prompt: review this agreement and tell me which clauses I should push back on. The agreement identifies a Customer and a Supplier, which does not
establish whom the user represents. Reply with ### Clarification needed and the
single question "Which party do you represent in this agreement: the Customer or the
Supplier?", and do not optimize until answered.
Clear, document-aware editing prompt. Source: Improve my prompt: revise clause 12 so the Customer gets 30 days to cure a payment breach. Keep everything else the same. The optimized prompt reads: "Revise clause 12 of the supplied agreement so
that the Customer has 30 days to cure a payment breach before the Supplier may
exercise the termination right addressed in that clause. Make only the minimum
changes needed to implement that cure period. Preserve all unaffected wording,
defined terms, numbering, formatting, and the clause's other legal effects. If clause
12 does not contain the relevant payment breach termination right, or the requested
change conflicts with another provision, identify the issue rather than guessing or
editing unrelated text. Return the proposed change as a reviewable edit." The
improvement bullets then note that the optimization fixed the target provision, the
exact legal outcome, the preservation requirements, conflict handling and the
expected edit output.
1---2name: improve-legal-prompt3description: >-4 Turns a rough request or an existing draft into one ready-to-use Cowork5 prompt, preserving the user's original legal objective while making document6 scope, party perspective, constraints, missing information handling and7 expected output explicit. Returns the prompt plus two or three improvement8 notes, and never runs it. Use when the user asks to "optimize my prompt",9 "rewrite my prompt for reviewing this agreement", "improve this prompt", "how10 should I ask Cowork to revise the termination clause", "clarify this11 instruction before I run it", or "why isn't my prompt working". Do NOT use for12 the legal work itself — "rewrite this clause" or "make this paragraph clearer"13 is edit-contract, a reasoned answer on a legal question is legal-reasoning,14 and reviewing an agreement is review-contract.15metadata:16 source: https://skillmd.com/skills/microsoft/improve-legal-prompt17 displayName: Improve legal prompt18 category: productivity19 icon: Scales20---2122# Improve legal prompt2324Convert the user's rough request or existing prompt into one ready-to-use prompt for25Cowork. Preserve the original objective while clarifying the intended legal outcome,26document scope, constraints, required inputs, handling of missing information, and27expected response format.2829This skill optimizes the prompt. It does not perform the legal analysis, review,30drafting or editing the prompt describes, and it never guarantees a legal outcome.3132## When NOT to Use3334Use this skill **only** when the user explicitly asks to create, improve, clarify,35diagnose or rewrite a prompt, instruction or request for Cowork.3637- `Rewrite my prompt for reviewing this agreement` — prompt optimization. In scope.38- `How should I ask Cowork to revise the termination clause?` — prompt optimization.39 In scope.40- `Rewrite this clause`, `make this paragraph clearer`, `improve the termination41 provision` — document editing. Use `edit-contract`.42- `Is this clause enforceable?`, `what does this mean for us?` — use43 `legal-reasoning`, or `explain-legal-concepts` for a plain language explanation.44- `Review this agreement` — use `review-contract`.45- A vague legal request does not become a prompt-optimization request merely because46 a better prompt might improve the result.4748**Hand-off rule.** If a request, or part of one, matches an item above that names49another skill, do not do that part here — even when the documents are already open50and the work looks quick. Name the skill that handles it (for example, "That part51is a job for `edit-contract`") and stop that part; finish only what belongs to52this skill. If the named skill is not installed, say so plainly and do not attempt53it here.5455## Step 1: Identify the source request5657- Treat text the user pastes, quotes, labels as a prompt, or describes as their58 instruction as the source.59- Where the turn refers to a prompt from the recent conversation, use the most recent60 unambiguous prompt under discussion.61- If the user gives a target task but no draft prompt, write the prompt from scratch.62- If neither a source prompt nor a target task is identifiable, ask exactly:63 `What prompt would you like me to optimize?`64- Preserve exact values, defined labels, clause numbers, field names, schemas,65 allowed values, word limits, exceptions and formatting requirements unless the user66 asks to change them. Never carry a personal identifier through into the optimized67 prompt: an optimized prompt is re-run downstream, so a national insurance or social68 security number, bank or payment card detail, home address, date of birth, salary or69 health datum copied out of the source request or a supplied document propagates into70 every later run. Replace it with a role or a neutral placeholder, keep the71 instruction intact, and say what you replaced and why; where the source prompt asks72 for such a field as an output, drop that field from the optimized prompt and say so.73 See **Personal data minimisation** in Guardrails.7475## Step 2: Use the supplied documents only to resolve context7677Read only what is needed to make the prompt accurate. Use `Glob` over `input/**/*`78and `grounding/**/*`, check for an attached OneDrive folder, and79read it in full. When opening a document, use a method that shows tracked changes and comments, and check whether any are present before relying on the text. Refer to80each file by its exact filename.8182- Use available context directly when it clearly resolves document type, party names,83 clause names, defined terms, or the location the user means.84- Read the specific file the user points at; read further files, or more of a long85 one, only to resolve an otherwise ambiguous reference or verify exact terminology.86- Include specific document terms in the optimized prompt where they materially87 improve precision.88- Do not broaden the optimization into a document review, and never infer which party89 the user represents or invent a legal or commercial position from the document.9091## Step 3: Decide whether clarification is essential9293Pause before optimizing when an ambiguity could materially change the legal outcome94or cause Cowork to act on the wrong text. Ask only for the material gaps that apply,95using a question card:9697- which party the user represents, or whose position the prompt should advance;98- which clause, section, document, attachment or passage is in scope;99- what outcome words such as `better`, `stronger`, `fairer` or `market standard` are100 intended to achieve;101- which jurisdiction applies, where the task depends on jurisdiction-specific law or102 execution requirements;103- which required commercial value, drafting position, remedy, fallback or source104 precedent should be used.105106Do not ask about preferences a sensible default covers, such as minor formatting or107whether the explanation runs to two or three bullets. Ask the smallest set of108questions needed, group related ones, and never repeat what the user already supplied109or the document already establishes. When clarification is essential, ask and **stop**110— do not also supply a knowingly unreliable prompt in the same answer.111112## Step 4: Build the Cowork prompt113114- Lead with the outcome the user wants Cowork to achieve.115- State the document scope precisely: a complete supplied document named by filename,116 a named provision, a quoted passage, specified attachments or precedents, or a117 general legal question.118- Include party perspective, legal or commercial objective, jurisdiction, audience,119 constraints and source material, where supplied or clarified.120- Separate hard requirements from preferences, so Cowork does not treat a stylistic121 preference as an inviolable legal constraint.122- State what Cowork must do when information is missing, inconsistent, ambiguous or123 requires judgement: identify the gap or ask, never guess.124- Make the expected response explicit — analysis, cited answer, issue table, proposed125 edits, questions for the user, draft language, or another named deliverable.126- For analysis or review, require conclusions grounded in the document text, with127 findings distinguished from assumptions and matters requiring judgement.128- For editing, state the intended legal effect and require the smallest necessary129 change, preserving unaffected wording, defined terms, numbering, formatting and130 substantive meaning.131- For drafting, identify what to create, the source material to follow, the intended132 position, and the facts Cowork must obtain rather than invent.133134## Step 5: Preserve the objective, then audit135136Keep every meaningful requirement from the source unless it conflicts with the user's137clarified goal. Remove repetition, vague filler and contradictions without changing138the legal position, ambition or scope. Do not add role-play, unnecessary disclaimers,139elaborate process, or deliverables the user did not request. If the user asked only140for clarity, improve clarity without turning the request into a different legal task.141142Before answering, check that: Cowork can tell what to do, what material to use, what143not to assume or change, and what to return; the prompt cannot reasonably be misread144as edit-when-analysis-was-wanted, analyse-when-edits-were-wanted, whole-document-when145one provision is in scope, or ask-the-user when an internal assessment was intended;146and no meaningful requirement, exact value, exception or output constraint was lost147against the source.148149## Step 6: Output format150151When essential information is missing, reply with exactly:152153```text154### Clarification needed155156[one to three concise, targeted questions]157```158159and include no optimized prompt until the user answers. Otherwise reply with exactly160these two sections:161162```text163### Optimized prompt164165[complete ready-to-copy prompt for Cowork]166167### Improvements made168169- [specific improvement]170- [specific improvement]171- [optional third specific improvement]172```173174Keep the explanation to two or three bullets explaining how the optimization175clarified behavior, scope, required inputs, missing information handling or output176shape — not generic prompt writing advice. Do not answer or execute the optimized177prompt, do not offer multiple variants unless asked, and stop after the improvement178bullets rather than offering to run it.179180## Guardrails181182- **Read-only, context only.** Inspect documents solely to resolve prompt context,183 reading only supplied files and only when necessary.184- **Never write to a document.** Do not edit, comment on or otherwise modify any185 document; optimizing a prompt must not change the document.186- **Not a legal answer.** Do not produce citations, answer metadata or a187 document-grounded legal conclusion — the output is a prompt.188- **No downstream execution.** Do not hand off to a review, relevance-generation or189 playbook-extraction workflow, and do not open progress tasks to run the downstream work.190- **Personal data minimisation.** Report what the documents say, not who people are.191 Never carry national insurance or social security numbers, bank or payment card192 details, home addresses, dates of birth, salary or health data into an answer, a193 table, a cell, a quotation, a summary, a draft or a suggested wording — including194 the optimized prompt itself and any example it embeds — even where they sit inside195 a matter document and even when the user names the field or asks for the column.196 Refer to individuals by name and role only. If such a detail is material to a197 finding, say that the source contains it and cite the provision rather than198 reproducing it; leave the requested field out and deliver the rest.199- **No assumed perspective.** Never infer the represented party merely because the200 document names the parties.201- **No guarantees.** Never claim the optimized prompt assures a correct legal202 outcome.203204## Worked examples205206**Essential party perspective is missing.** Source:207`Rewrite my prompt: review this agreement and tell me which clauses I should push208back on.` The agreement identifies a Customer and a Supplier, which does not209establish whom the user represents. Reply with `### Clarification needed` and the210single question "Which party do you represent in this agreement: the Customer or the211Supplier?", and do not optimize until answered.212213**Clear, document-aware editing prompt.** Source: `Improve my prompt: revise clause21412 so the Customer gets 30 days to cure a payment breach. Keep everything else the215same.` The optimized prompt reads: "Revise clause 12 of the supplied agreement so216that the Customer has 30 days to cure a payment breach before the Supplier may217exercise the termination right addressed in that clause. Make only the minimum218changes needed to implement that cure period. Preserve all unaffected wording,219defined terms, numbering, formatting, and the clause's other legal effects. If clause22012 does not contain the relevant payment breach termination right, or the requested221change conflicts with another provision, identify the issue rather than guessing or222editing unrelated text. Return the proposed change as a reviewable edit." The223improvement bullets then note that the optimization fixed the target provision, the224exact legal outcome, the preservation requirements, conflict handling and the225expected edit output.