Tessl • The management layer for AI agent skills

SkillPublic

hard-conversations

Writes you a ready-to-use script for a feedback or hard conversation, then rehearses the pushback. Use when you need to give tough feedback, confront a peer, tell a report they are underperforming, deny a promotion, prepare to fire someone, say no to your boss, ask for feedback, or repair a conversation that went badly. Draws on 66 Lenny's Podcast guests including Kim Scott, Carole Robin and Alisa Cohn.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, highly actionable instruction skill with a clear diagnose-dispatch-execute workflow, embedded self-tests, and well-signaled one-level-deep references. The only improvements are removing the inline Receipts section (duplicating quotes.md) and tightening the slight overlap between the Step 2 table and the Run-it sections.

Suggestions

Move the 'Receipts' quotes into references/quotes.md and replace them with a one-line pointer, cutting duplication and body length.

Trim the Step 2 play table's 'Why' column or merge it with the section headers to reduce the overlap between the dispatch table and sections A-G.

Dimension	Reasoning	Score
Conciseness	Nearly every line carries a framework, attribution, or word-for-word script with no padding explaining concepts Claude already knows; minor trims exist, e.g., the 'Receipts' quotes duplicate references/quotes.md and the Step 2 play table partially restates sections A-G.	4 / 5
Actionability	Fully actionable for an instruction-only skill: copy-paste scripts ('when you [specific behavior], I feel [one feeling word], and I'm telling you because...'), exact go-to questions, a fill-in deliverable brief template, and a graded 8-criterion scoring rubric with 1/3/5 anchors covering all common cases.	5 / 5
Workflow Clarity	Clear sequence (Diagnose with max 4 questions -> Pick the play via a dispatch table -> Run it with prep and scenario sections), plus a reaction playbook for when it 'gets hot' and explicit self-checks ('net test', 'if the honest answer to have I been crystal clear is sort of, you have not') that serve as validation steps.	5 / 5
Progressive Disclosure	Both 'Go deeper' references (references/frameworks.md, references/quotes.md) are real files, one level deep, and clearly signaled with descriptions; the minor gap is the inline 'Receipts' quote section, which duplicates content that belongs in references/quotes.md.	4 / 5
	Total	18 / 20 Passed

Description

81%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit what/when structure and excellent natural trigger coverage. Its main flaw is second-person voice ('Writes you...', 'Use when you need...'), which the rubric penalizes on specificity, and the what-clause lists only two concrete actions.

Suggestions

Rewrite in third person (e.g., 'Writes a ready-to-use script for a feedback or hard conversation, then rehearses the pushback') to remove the second-person voice penalty.

Add one or two more concrete actions to the what-clause (e.g., 'grades an existing draft against an 8-criterion rubric and returns the top fixes') to lift specificity from anchor 3 toward anchor 4-5.

Dimension	Reasoning	Score
Specificity	The description names the domain and 1-2 concrete actions ('Writes you a ready-to-use script... then rehearses the pushback'), matching anchor 3, but it is written in second person ('Writes you', 'Use when you need'), which the judging guidelines penalize by reducing specificity by 1.	2 / 5
Completeness	Explicitly answers both what ('Writes you a ready-to-use script... then rehearses the pushback') and when ('Use when you need to...') with concrete trigger phrases, matching the anchor-5 example structure exactly.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural phrases users would actually say: 'give tough feedback, confront a peer, tell a report they are underperforming, deny a promotion, prepare to fire someone, say no to your boss, ask for feedback, or repair a conversation that went badly', with synonyms (tough feedback / hard conversation / pushback).	5 / 5
Distinctiveness Conflict Risk	A clear niche (hard workplace conversations) with distinct triggers like 'deny a promotion' and 'prepare to fire someone'; minor overlap risk remains with adjacent communication skills for phrases like 'ask for feedback'.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: menkesu/awesome-pm-skills
Path: skills/hard-conversations/SKILL.md
Revision: c1b6e2d

Reviewed: 4 days ago

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

hard-conversations

Table of Contents

Is this your skill?