Works with the AI Agents you already use
manager feedback and coaching prompt builder
This skill screens manager-authorized observations through a deterministic engine to produce behavior-based Situation-Behavior-Impact (SBI) statements and coaching questions.
$1.99
manager feedback and coaching prompt builder
Example session with this skill installed
Prepare a development conversation for employee REF-8821. I have three notes from June regarding their missed deadlines and one positive note about their technical documentation quality.
- Read your context and instructions
- Compiled the manager feedback
I have processed the observations for REF-8821. I identified 3 developmental notes and 1 positive note. One note regarding "attitude" was excluded as judgmental wording.
Feedback and Coaching Preparation — REF-8821, 2024-06-15
1. Scope, authorisation and assumptions
- Sources: E1, E2, E3 (Direct Observation)
- Intended Use: development_conversation
- Jurisdiction: US-NY. Jurisdiction review by HR or legal counsel is required.
- Authorised by: Manager M. Smith.
2. Observation screening
| Id | Theme | Valence | Date | Status | Reasons |
|---|---|---|---|---|---|
| E1 | Timeliness | Developmental | 2024-06-02 | Usable | - |
| E2 | Documentation | Positive | 2024-06-05 | Usable | - |
| E3 | Communication | Developmental | 2024-06-10 | Excluded | Judgmental wording |
Counts: Submitted (4), Authorized (4), Usable (3), Excluded (1).
Metrics: Positive Share: 33%, Median Age: 8 days.
3. Evidence by theme
| Theme | Valence | Usable | Verified | Distinct dates | Evidence |
|---|---|---|---|---|---|
| Timeliness | Developmental | 2 | Yes | 2 | E1, E4 |
| Documentation | Positive | 1 | Yes | 1 | E2 |
4. Draft feedback frames
Frame 1: Timeliness (Developmental)
- Evidence: E1, E4
- Situation: During the Q2 sprint planning and the client delivery phase.
- Behavior: Project milestones were submitted 48 hours after the agreed deadline.
- Impact: The QA team had reduced testing time, resulting in two hotfixes post-launch.
- Coaching Questions:
- Goal: What does a successful delivery timeline look like for you?
- Reality: What specific blockers appeared in the last 48 hours of the sprint?
Analytical estimate — validation required. Draft, requires manager approval.
5. Fair process checklist
| Item | Status |
|---|---|
| Specific and dated facts | Pass |
| Opportunity to respond | manager_to_confirm |
| Balanced valence | Pass |
6. Warnings, exclusions and items for human review
- W01: Judgmental terms removed from E3. Invite manager to restate "unprofessional" as observable behavior.
- Review: Ensure employee has no active protected leave before delivery.
This preparation supports, and does not replace, the manager's judgment, HR advice and the employee's right to respond.
Next steps
- Restate the excluded note E3 as a specific observable behavior if you wish to include it.
- Review the SBI drafts to ensure they match your direct observations.
- Schedule the conversation and share these points as a draft for discussion.
Connects securely to your tools. The creator never sees your data.
About this skill
Managers often struggle to convert raw notes into objective, actionable feedback. This skill screens manager-authorized observations through a deterministic engine to produce behavior-based Situation-Behavior-Impact (SBI) statements and coaching questions.
What it does
- Screens observations by checking for authorization, dates, and completeness while stripping out judgmental or sensitive language.
- Drafts feedback frames using the Situation-Behavior-Impact (SBI) model to ensure clarity and objectivity.
- Generates coaching questions based on the GROW model (Goal, Reality, Options, Will) mapped to specific behaviors.
- Grades evidence quality by distinguishing between patterns, single occurrences, and unverified third-party reports.
- Identifies fair-process gaps to ensure feedback is balanced, dated, and lacks personality-based judgments.
How it works
- Input gathering: The user provides dated behavior notes, employee reference codes, and authorization status.
- Data validation: The agent maps notes to themes and valences, ensuring no sensitive or protected characteristics are included.
- Execution: The agent runs
scripts/run.pyto process therequest.jsonthrough fixed rules and templates. - Report generation: The agent outputs a structured Markdown report including evidence tables, drafted frames, and process warnings.
Frameworks & tools
The skill utilizes a Python-based logic engine (scripts/run.py) and adheres to the Situation-Behavior-Impact (SBI) and GROW coaching frameworks. Data structures follow strict JSON schemas for input and output validation.
Why this beats prompting it yourself
Generic prompts often hallucinate employee motives or introduce biased personality labels. This skill uses a deterministic script and fixed templates to ensure feedback remains strictly behavioral, evidence-graded, and compliant with fair-process standards.
Use cases
- Prepare for a formal development conversation or performance check-in.
- Convert subjective manager notes into observable, factual behavior statements.
- Identify information gaps where third-party reports lack organizational validation.
- Generate structured coaching questions for a specific performance theme.
Known limitations
Does not handle employment decisions like pay, discipline, or termination. Requires manual manager authorization for every observation. Group statistics are suppressed for small sample sizes.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
No support for pay, discipline, or termination decisions. Requires manager-authorized dated notes. Suppresses small-group aggregates. Drafts only; requires human approval.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 days ago